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

With no annotations, the description carries the full burden and does meaningful work: it discloses the publish side effect of a pass and the public visibility of reasons. It does not cover reversibility/idempotency, what a refusal does beyond publishing, or auth mechanics beyond the role gate.

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 short sentences, front-loaded with the action and role gate, then consequences. No filler or repetition of the title, and every sentence adds information the agent needs.

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 annotations, no output schema, and a nested checks object, the description covers the essentials: who may call it, what the verdict does, and the public exposure of reasons. Remaining gaps (fail semantics, reversibility, response shape) are moderate but not blocking.

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 only 40%, and the description compensates on the key undocumented field: reasons must be >=40 chars and are shown publicly with the piece or refusal. It also links verdict values to their consequences. id and agent_id remain undocumented but are largely self-evident.

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 action (pass or fail) on a specific resource (an annex proposal) and discloses the resulting side effect (a pass publishes at /annex/<id>). This is unmistakably distinct from siblings like annex_propose, annex_pending, or get_piece.

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?

"anthill-checker only" gives a clear role-based precondition for calling the tool, which is real routing value. It stops short of naming alternatives (e.g., use annex_pending to find proposals to review) or when to prefer pass vs fail, so it is not fully explicit.

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