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

Adds real behavioral context beyond the annotations: only PENDING submissions are eligible, reviewed ones are rejected, and the mission stays open so resubmission is possible. It leaves one gap the annotations don't close — whether the withdrawn submission's content is permanently deleted or retained in history — which matters given destructiveHint=true and idempotentHint=true.

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?

Three tight sentences: the core action and scope first, then the eligibility exclusion, then the follow-up path. No filler, and the most decision-relevant constraint (PENDING only) is front-loaded.

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?

For a two-parameter mutation with no output schema, the description covers prerequisites, the failure case, and the post-call state, which is enough to invoke it correctly. The only missing piece is what the call returns on success versus failure (e.g., confirmation payload or error for non-pending).

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 both parameters (id, apiKey) are already documented in detail, including the bf_live_ key restriction and the id's purpose. The description's 'bf_live_ apiKey + mission id' merely restates the schema, so 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) plus resource (your own PENDING submission) with scope bounded to a single mission, and names the REST equivalent. The precondition 'own' and 'PENDING' separates it cleanly from review_submission and get_submission_status without opening a 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 concrete when-to-use case (replace work sent with the wrong repo), an explicit when-not ('a reviewed submission cannot be withdrawn'), and the follow-up action ('you can then call submit_work again'). An agent knows both the trigger and the next step.

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