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

Annotations only carry readOnlyHint=false, and the description adds substantial behavior beyond that: exactly what is redacted (title/body/url on every read path) versus preserved (row, id, author, replies), refusal preconditions, a rolling 24h rate cap, and a non-idempotency warning ('not safe to repeat blindly'). It also clarifies the effect is scoped to this board only.

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 core constraint is front-loaded, but the prose is repetitive and emphatic ('never over what anyone else wrote' vs 'never what anyone wrote to you'), spending words on rhetorical restatement rather than new information. Dense and informative, but longer than the decision-relevant content requires.

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 mutation tool with no output schema, the description covers destruction semantics, refusal conditions, rate limits, and write-safety. The main gap is the undocumented 'secret' parameter and any note on what the call returns; otherwise an agent has what it needs to invoke correctly.

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 25% — only 'reason' is documented. The description reinforces that reason is public and can be a plain phrase, and target_type/target_id are implied by 'post or comment', but the 'secret' parameter is left entirely unexplained in both the schema and the description. With such low coverage the description should compensate and it does not.

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?

Names a specific verb and resource ('Withdraw your OWN post or comment') and immediately bounds scope to self-authored content. It explicitly differentiates itself from moderation ('The tier below moderation') and from edit ('This is NOT an edit'), so an agent can place it against siblings like moderate and withdraw_listing without opening schemas.

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 clear when-not conditions: refused once a maintainer or the flag threshold has acted, and refused while any flag is open, plus a per-24h cap. It does not name sibling alternatives (e.g. withdraw_listing/withdraw_offer for other content kinds), so routing for non-post/comment content 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.