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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety and repeatability are covered by structured data. The description adds the meaningful behavioral detail that the answer may be absent until processing completes, so a partial response is possible. It does not say whether polling is expected, what the possible state values are, or how long results persist.

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 compact sentence with the object of retrieval front-loaded and no filler. The phrasing 'The state and, once ready, the answer' is slightly elliptical and would read better as a full clause, but nothing is wasted.

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 no output schema, the description must convey the return shape, and it does so only at a high level: a state plus a conditional answer. The state vocabulary (pending, running, failed, ready) and failure behavior are left unstated, which is a real gap for a polling-style 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?

Two of three parameters are documented in the schema (app_id, notebook_id); query_job_id has no schema description, and the description only indirectly implies it is the job id returned by ask_knowledge_notebook. That is a useful semantic link, but it is not stated plainly, so the description only partially compensates for the 67% coverage.

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 precisely (the state and, when ready, the answer of a knowledge question) and ties it to the originating call, ask_knowledge_notebook. An agent can distinguish it from the ask tool and from get_job_status without opening the schema. The verb 'get' is only implied, which keeps it 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?

The mention of 'asked with ask_knowledge_notebook' and 'once ready' implies this is a follow-up/polling call for a job created elsewhere, which is useful routing information. However, it never states explicitly that it should be called after ask_knowledge_notebook or repeated until the state becomes ready, and no when-not-to-use guidance is given.

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