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

Beyond readOnlyHint=true and openWorldHint=false, the description adds two things the annotations cannot: the call must use the same API key that submitted the job (an auth constraint), and it is not billed (cost behavior not visible anywhere else). The 'status and, once complete, the answer' phrasing also discloses the asynchronous, poll-until-ready nature of the response.

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 dense sentences with no filler. The return-value contract comes first, the auth prerequisite second, the cost note last — every clause carries distinct information.

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?

Absent an output schema, the description has to describe the payload, and it does so reasonably: status now, answer and cited passages later. It stops short of enumerating possible status values or telling the agent how to tell 'not ready' from 'failed', which is the one gap for a polling tool.

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?

With schema description coverage at 0% for job_id, the description has to carry the load. It does add the key fact that job_id identifies a job created by ask_question, but says nothing about the format, length constraints, or how to obtain the id — it never names ask_question's output field.

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 names the resource (a job from ask_question) and enumerates what comes back: status, then the answer plus cited passages once complete. That is enough to tell it apart from the sibling ask_question, which creates the job. The verb is implied rather than stated (no 'retrieve'/'poll'), which keeps it just short of a 5.

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?

Mentioning that the job comes 'from ask_question' implies the intended sequence, and 'Needs the API key that asked' is a real prerequisite. There is no explicit polling guidance, no statement of what to do while status is incomplete, and no named alternative, so usage is implied rather than prescribed.

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