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

Annotations only carry destructiveHint=false, so the description does the heavy lifting: it discloses access restriction ('Internal Coderbuds staff only'), the non-binding nature of the write ('does not govern anything until a person adopts it'), where the proposal surfaces, and the consequence of omitting evidence ('shown as ungrounded rather than quietly passing as fact'). That is real behavioral context an agent cannot get from the annotation.

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?

Front-loaded with scope and the adoption caveat before the when-to-propose rules, and nearly every sentence carries instruction. It runs long across four blocks, and the evidence explanation partially duplicates the schema's own wording, so it is dense rather than maximally tight.

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?

With no output schema, the description does explain the outcome (a proposal on the admin tab, ungrounded flagging when evidence is absent), which is the main thing an agent needs. It never says what the call returns (an id, a link, a confirmation), which is the one remaining gap for a create-style tool.

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 100%, so the baseline is 3; the description still adds meaning — it explains what makes evidence valid ('the reply you read, the measurement, the count of rows'), the cost of leaving it out, and the required form of statement (an instruction the next draft can follow, not an observation, with a usable vs unusable example). 'kind' and 'source_url' get no treatment in 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 — proposing a rule about who Coderbuds is for or what an opener may say — and pins down the destination (the Who it is for tab of /admin/prospects as a proposal). It implicitly separates itself from writing/adopting rules, but never names the sibling read or standard-setting tools (get-icp-tool, set-change-fit-standard-tool) an agent might otherwise reach for.

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 an explicit trigger ('propose when outbound has taught you something the current rules do not say: a reply that contradicts a wedge, a disqualifier that keeps recurring, a signal that keeps producing rows nobody writes to') and two explicit exclusions: no tidier rewording of an existing rule, and no re-proposing anything in 'retired'. When/when-not guidance is complete.

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