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

Annotations already declare readOnly, idempotent and non-destructive, but the description adds real behavioral context beyond them: it blocks up to 20 seconds for a nearly-finished short answer, Ultradeep reviews take minutes, and it can return either the finished answer with numbered sources or an in-progress status. Missing error behavior for an invalid or unknown question_id, which keeps it from a 5.

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 usage trigger is front-loaded before the behavioral detail, and the content is appropriately short. The stacked colons make the middle clause slightly run-on, but nothing is redundant.

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 carries the burden of explaining returns and does so (numbered sources, or in-progress status), plus timing expectations. It is complete for its purpose, lacking only failure-mode detail.

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 100% and the single parameter is fully documented in the schema, so the baseline is 3. The description only echoes the schema by tying question_id to the tools that produced it, adding little syntax or format detail.

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?

States a specific verb and resource ('it reads that question's answer by the question_id they gave') and explicitly ties itself to the producing siblings ask_arn and start_ultradeep. An agent can distinguish this retrieval tool from the ones that create the answer without opening the schema.

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?

Gives a clear when-to-use condition – when ask_arn or start_ultradeep said an answer is still being written, or the user wants it again – which routes the agent correctly. It does not state a when-not (e.g. for listing all questions, implying list_questions), so it stops short of the full 5.

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