Open Creator Graph docs

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuinely new context: the response is the complete page rendered as Markdown, which matters given there is no output schema. It omits error behavior for an invalid path, keeping it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with the action and output format before the parameter detail. The long enumeration of fixed paths is bulky but earns its place as the only documentation of valid non-search inputs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter read tool with full annotations and no output schema, the description covers what the tool does, where the input comes from, and what comes back. Only the failure mode for an unknown path is left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the single parameter — and it does, defining `path` as either a search_docs-returned path or one of the enumerated canonical paths, with leading-slash form shown by example. It doesn't mention the 200-character limit or that no query strings/fragments are accepted.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Read one documentation page") plus the return format ("in full, as Markdown"). The singular "one page" scope cleanly separates it from the sibling search_docs, which returns many results.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes the agent: `path` comes from a prior search_docs call, and it enumerates the fixed entry points usable without searching. It stops short of stating exclusions (e.g., don't use this to search, don't pass external URLs), but the intended workflow is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered by structured data. The description adds corpus scope (llms.txt, llms-full.txt, reuse terms) but nothing about ranking, result shape, or the fact that limit caps at 10.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with the verb first and scope second; the parenthetical file list is informative rather than filler, though the trailing topic enumeration makes it slightly dense.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description should indicate what a hit looks like (snippet, source file, link) but does not. Combined with the unaddressed parameter semantics, it is adequate to identify the tool but incomplete for confident invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden for query and limit, and it says nothing: no guidance on what query strings work well (maxLength 200), and no explanation that limit is a result count defaulting to 5 with a maximum of 10. The topics list hints at what can be searched but does not explain the parameters themselves.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description pairs a specific verb ("Search") with a named resource ("Open Creator Graph's FAQ and machine documentation") and enumerates the concrete files and topics covered, so an agent can tell it retrieves documentation rather than graph records. It stops short of differentiating itself from the sibling fetch_doc, which it never mentions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"for questions about how records, confidence labels, AI consent, removals and reuse work" implies when to reach for it, but there is no explicit when-not guidance and no reference to fetch_doc as the alternative for retrieving a specific document rather than searching.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.