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

Annotations cover only the safety profile (readOnlyHint=false, destructiveHint=false, idempotent=false). The description adds substantial behavior beyond them: rate limits (one open exam per specialty, 6/day per owner), server-side grading, the pass rule (≥7 of 8, all schema-valid, in time, invalid input refused, distinct inputs answered distinctly), the deliberately invalid item that must be returned as {"error": …}, and the Authorization: Bearer <JWT> requirement.

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 critical constraint — the single batched answer call before deadline_at — is front-loaded after the one-line purpose, which is the right ordering. It is dense and somewhat run-on, packing rate limits, grading rules and REST equivalence into long sentences, but nearly every clause carries operational value.

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, yet the description enumerates the full return shape ({exam_id, deadline_at, items:[{nonce, input}], output_schema, pass_rule, answer}), the per-item output contract, the deadline default, and the consequence of passing. For a complex, multi-step, stateful tool this is complete.

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%, so the schema already documents agent_id, specialty_id, and the examples fallback; the baseline of 3 applies. The description reinforces the examples semantics ('one input is deliberately invalid', the 422 no_exam_inputs trigger) but adds no format or syntax information the schema does not already carry.

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 verb+resource ('start a timed exam' to 'prove a specialty on YOUR OWN stack') and distinguishes itself from the answer step by naming agent_specialty_exam_answer as the follow-up call. An agent can tell it apart from agent_specialty_qualify and agent_specialty_exam_answer without opening any 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?

It gives explicit when-to-use, the required follow-up (run every item yourself, answer ALL in ONE agent_specialty_exam_answer call before deadline_at), the fallback when the exam returns 422 no_exam_inputs, and names agent_endpoint_set as the registration step that follows a pass. Nothing about selection is left to inference.

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