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

Annotations already mark the tool read-only and non-destructive. The description adds genuinely useful behavioral detail: it returns a working link, extraction/readability status, cached document text, optional excerpts, and switches to a newest-first document list when no selector is provided. No contradiction with annotations.

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 description is four sentences with no filler: core retrieval purpose, return contents, text_query usage, and serial_number fallback. Each sentence earns its place and the most important information is front-loaded.

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 compensates by naming the return fields explicitly. It also explains the input-omission mode, which is essential for correct invocation. With read-only annotations covering safety and the schema documenting all parameters, nothing critical is missing.

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 coverage is 86%, so parameters are already largely defined. The description adds meaning beyond the schema by identifying document_id as the stable exact selector, explaining that omitting all selectors returns a list, and clarifying that text_query produces excerpt-centered results. It doesn't add detail for max_chars, but schema bounds cover that.

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 states a specific action and resource: retrieve one specific USPTO prosecution document by stable document_id, and enumerates the selectors and return fields. The fallback behavior (serial_number alone returns a pickable list) clearly distinguishes it from list_prosecution_documents and other retrieval siblings.

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?

The description explicitly tells the agent when to use text_query (when the user asks what a document says about an issue) and when serial_number alone is sufficient, removing the need for a separate list_prosecution_documents call. It does not contrast with get_latest_office_action or research_office_action, but the single-document scope is clear enough.

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