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

While annotations already declare read-only, idempotent, open-world, and non-destructive behavior, the description adds worthwhile behavioral specifics: it returns 'user_ask and ia_response', including that ia_response is null if the answer is not in the document. It also exposes the POST endpoint. This goes beyond the annotations without contradicting them.

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 three sentences and every sentence contributes meaningful information: what the tool does, the prerequisite, the size limits, and the return value structure. No filler or redundancy. It is front-loaded with the main purpose.

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?

Given the low complexity (3 parameters, simple array input) and rich annotations plus an output schema, the description covers the essential behavioral contract: usage prerequisite, question limits, response fields, and null result meaning. The tool is simple enough that this is a complete description.

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 100%: the schema already documents api_key with an example, document_id as a UUID with a concrete example, and questions with array constraints and an example. The description only repeats the 400-character and 5-question limits already present in the schema, so it adds little new parameter meaning.

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 opens with a specific action verb and resource: 'Ask up to 5 questions about a persisted document', and identifies the exact HTTP endpoint. It clearly distinguishes this from sibling extraction and document-creation tools by specifying the Q&A-over-persisted-document use case.

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 states an explicit prerequisite: 'Requires document_id from an extraction with window_context'. It also constrains usage with the 5-question limit and the 400-character per-question rule. It does not explicitly contrast with alternatives, but no sibling tool performs the same persisted-document Q&A function, so usage context is adequate.

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