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

Annotations already declare the safety profile (readOnly=false, destructive=false, idempotent=false), so the description's job is to add state-machine context — and it does: the story must still be queued, and cancellation refunds the fee. It doesn't discuss retry/idempotency behavior or error responses, which is a minor gap given annotations cover that flag.

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 short sentences, front-loaded with the action and its refund, then the time limit. No wasted words.

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 described. For a single-param mutation, the description covers the key state precondition and outcome; only failure/retry semantics are left implicit.

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?

One required parameter with 100% schema description coverage, so the schema already defines 'id'. The description adds no extra meaning about the identifier (e.g. that it must reference a queued post) — baseline 3 applies.

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 ('withdraw') and resource ('a story still queued for moderation') plus the side effect (fee refund), which clearly separates it from delete_post or report_post. It stops short of naming a sibling explicitly, so it is clear but not fully differentiated by comparison.

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?

'Still queued for moderation' and 'Too late once moderation has decided' give an explicit precondition and an exclusion condition. It does not name the alternative action to take when cancellation is too late, which keeps it below a 5.

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