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

Annotations already cover readOnly/idempotent, but the description adds what they cannot: the 60-120s async pass with an immediate job_id, the four status values and what each means operationally, why 'lost' happens (worker replaced by a deploy) and the required recovery, and that polling is free while re-running review_post is a paid duplicate write.

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?

Purpose is front-loaded and nearly every sentence carries distinct information. The final sentence about double-running review_post is really usage guidance that duplicates the expense theme already implied earlier, so it is slightly redundant within the passage.

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?

An output schema exists, so return values need not be explained, yet the description still summarizes status semantics — exactly the part an agent must branch on. Combined with timing, cost, and failure recovery, nothing needed to invoke or retry correctly is missing.

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 reported as 0% for the nested request object, so the description has to carry meaning — and it does: preferred vs fallback semantics for job_id/post_id, mutual exclusivity ('exactly one ... is accepted'), and what post_id resolves to (most recent job for that post). Gains a small deduction only because the type/shape detail lives in the schema, not the prose.

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 ('Collect the result of a review_post run') and immediately binds it to the sibling pair (review_post starts, get_review_status collects). No sibling ambiguity remains after the first two sentences.

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?

Explicit precedence rules: job_id preferred, post_id fallback when the handle is lost, exactly one accepted. It also names the failure mode to avoid ('calling review_post again for the same post while a job is running runs a second paid pass'), which is a genuine when-not-to-use instruction.

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