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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds nothing beyond the path: no indication of what search-text returns, how matching is performed, or whether results are paginated, so its incremental value is minimal.

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?

The text is short but the leading content is the same string repeated verbatim, which is pure waste, followed by an operation UUID that carries no meaning for an agent choosing a tool.

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?

With nested objects in the schema, no output schema, and an untyped free-form query object, the description would need to carry the meaning of the request payload. It does not, so an agent cannot construct a correct call from this definition alone.

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% and there are two parameters, including an opaque free-form `query` object with additionalProperties {} and a required `id`. The description compensates for none of this, leaving the shape and purpose of `query` entirely undocumented.

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 only restates the endpoint path "GET /api/files/:id/search-text" twice, which is effectively a tautology of the tool name and title. It conveys the resource (a file) and a sub-resource (search-text) but never says what the operation actually does or how it differs from close siblings like get_files_by_id_extract_text or get_files_by_id_view.

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?

There is no guidance on when to use this tool versus extract_text, view, or links variants on the same file. The only routing hint is the trailing note that describe_operation provides native request schemas, which points at a schema-fetching tool rather than giving any use-case conditions.

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