{
  "$schema_doc": "https://gtmstacker.com/registry/schema/entry.schema.json",
  "stability": "emerging",
  "generator": "agentic-media-registry",
  "generated_at": "2026-09-08T00:00:00Z",
  "id": "com.gtmstacker.registry/news/apple-agent-seer-tool-calling",
  "type": "news",
  "slug": "apple-agent-seer-tool-calling",
  "canonical_url": "https://gtmstacker.com/registry/news/apple-agent-seer-tool-calling/",
  "title": "Apple 'Agent Seer' research: API and parameter design break agent tool-calling",
  "description": "Apple research reporting that a large share of agent tool-calling failures trace to API and parameter design — schema shapes, parameter naming and documentation — rather than model capability. Practical implication for GTM-agent builders: design tool surfaces for the model, and keep a human approval step on consequential actions.",
  "category": "ai-infrastructure",
  "tags": [
    "ai-infrastructure",
    "news",
    "agents",
    "governance"
  ],
  "status": "active",
  "revision": 1,
  "content_hash": "e59311086ee31bcb941f25da685bc58e6e85908dbc6015d8e3c25081d1d3e134",
  "date_published": "2026-09-01T00:00:00Z",
  "date_modified": "2026-09-01T00:00:00Z",
  "source": {
    "name": "X · @IntuitMachine (research summary)",
    "url": "https://x.com/IntuitMachine/status/2094727051987108244"
  },
  "one_liner": "Apple research reporting that a large share of agent tool-calling failures trace to API and parameter design — schema shapes, parameter naming and…",
  "open_source": "unknown",
  "self_hostable": "unknown",
  "pricing_model": "unknown",
  "aliases": [],
  "alternatives": [],
  "secondary_categories": [],
  "lead": "Apple research reporting that a large share of agent tool-calling failures trace to API and parameter design — schema shapes, parameter naming and documentation — rather than model capability. Practical implication for GTM-agent builders: design tool surfaces for the model, and keep a human approval step on consequential actions.",
  "chunks": [
    {
      "index": 0,
      "heading_path": [],
      "est_tokens": 83,
      "text": "Apple research reporting that a large share of agent tool-calling failures trace to API and parameter design — schema shapes, parameter naming and documentation — rather than model capability. Practical implication for GTM-agent builders: design tool surfaces for the model, and keep a human approval step on consequential actions."
    },
    {
      "index": 1,
      "heading_path": [
        null,
        "Notes"
      ],
      "est_tokens": 149,
      "text": "Apple research reporting that a large share of agent tool-calling failures trace to API and parameter design — schema shapes, parameter naming and documentation — rather than model capability. Practical implication for GTM-agent builders: design tool surfaces for the model, and keep a human approval step on consequential actions.\n\n- Summarised from an X research thread (2026-09-01); the primary paper was not independently verified for this entry — treat specific failure percentages as unconfirmed.\n- Curated from the GTM Stacker signal registry (registry_update pass, briefs 2026-09-01→08)."
    }
  ],
  "alternates": {
    "markdown": "https://gtmstacker.com/registry/news/apple-agent-seer-tool-calling/index.md",
    "html": "https://gtmstacker.com/registry/news/apple-agent-seer-tool-calling/",
    "json": "https://gtmstacker.com/registry/news/apple-agent-seer-tool-calling/index.json"
  },
  "jsonld": {
    "@context": "https://schema.org",
    "@graph": [
      {
        "@type": "WebSite",
        "@id": "https://gtmstacker.com/#website",
        "url": "https://gtmstacker.com/",
        "name": "GTM Stacker Agent Registry",
        "description": "A daily-updated, agent-native registry of open-source tool discoveries, tool updates, and curated news for the go-to-market / RevOps engineering niche. Machine-readable first: agents can discover, parse, page, and delta-sync it without scraping HTML.",
        "inLanguage": "en",
        "publisher": {
          "@id": "https://gtmstacker.com/#organization"
        }
      },
      {
        "@type": "Organization",
        "@id": "https://gtmstacker.com/#organization",
        "name": "GTM Stacker",
        "url": "https://gtmstacker.com",
        "alternateName": "Agent-native registry of open-source go-to-market tools",
        "description": "GTM Stacker is an agent-native media property that maintains a daily-updated registry of open-source go-to-market, RevOps, sales, and marketing tools, engineered so both people and AI engines can discover, compare, and cite each tool.",
        "foundingDate": "2024-08",
        "knowsAbout": [
          "go-to-market engineering",
          "RevOps",
          "sales automation",
          "marketing operations",
          "open-source software",
          "AI agents"
        ],
        "founder": {
          "@type": "Person",
          "@id": "https://gtmstacker.com/#founder",
          "name": "Theo Popov",
          "jobTitle": "Founder",
          "url": "https://gtmstacker.com/about/",
          "sameAs": [
            "https://www.linkedin.com/in/theo-popov/",
            "https://x.com/Theo_Popov",
            "https://github.com/theopopov"
          ],
          "worksFor": {
            "@id": "https://gtmstacker.com/#organization"
          }
        },
        "mainEntityOfPage": "https://gtmstacker.com/registry/about/"
      },
      {
        "@type": "NewsArticle",
        "@id": "https://gtmstacker.com/registry/news/apple-agent-seer-tool-calling/#article",
        "headline": "Agent failures often trace to tool/API design, not model capability",
        "description": "Apple research reporting that a large share of agent tool-calling failures trace to API and parameter design — schema shapes, parameter naming and documentation — rather than model capability. Practical implication for GTM-agent builders: design tool surfaces for the model, and keep a human approval step on consequential actions.",
        "url": "https://gtmstacker.com/registry/news/apple-agent-seer-tool-calling/",
        "isPartOf": {
          "@id": "https://gtmstacker.com/#website"
        },
        "datePublished": "2026-09-01T00:00:00Z",
        "dateModified": "2026-09-01T00:00:00Z",
        "author": {
          "@id": "https://gtmstacker.com/#organization"
        },
        "publisher": {
          "@id": "https://gtmstacker.com/#organization"
        }
      },
      {
        "@type": "BreadcrumbList",
        "@id": "https://gtmstacker.com/registry/news/apple-agent-seer-tool-calling/#breadcrumb",
        "itemListElement": [
          {
            "@type": "ListItem",
            "position": 1,
            "name": "GTM Stacker Registry",
            "item": "https://gtmstacker.com/registry/"
          },
          {
            "@type": "ListItem",
            "position": 2,
            "name": "AI Infrastructure",
            "item": "https://gtmstacker.com/registry/category/ai-infrastructure/"
          },
          {
            "@type": "ListItem",
            "position": 3,
            "name": "Apple 'Agent Seer' research: API and parameter design break agent tool-calling",
            "item": "https://gtmstacker.com/registry/news/apple-agent-seer-tool-calling/"
          }
        ]
      }
    ]
  },
  "news": {
    "headline": "Agent failures often trace to tool/API design, not model capability"
  }
}