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

Beyond the lone destructiveHint=false annotation, it discloses the audience restriction (internal Coderbuds staff only), the landing surface (/admin/self-review), and crucially that the write is staged as 'proposed' with nothing happening until a human accepts it — exactly the state-transition context an agent needs before writing. It does not cover what happens on accept/reject or whether duplicate proposals are rejected server-side.

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 the audience gate and the definition, then usage rules, then parameter notes — the ordering matches how an agent decides. It is slightly redundant in re-explaining `claim` and `evidence` already covered by the schema.

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 six-parameter mutation with no output schema, the description covers who may call it, what it creates, the pending-state lifecycle, and when not to call it. The remaining gap is what the tool returns and whether it deduplicates against existing findings, which the agent must infer.

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 all six parameters are already documented in structured data, setting the baseline at 3. The description's restatement of `claim` and `evidence` ('leave it out rather than invent it') mirrors the schema text rather than adding new semantics such as expected evidence format or severity selection guidance.

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?

The description states a specific verb (propose) and defines the resource precisely: a claim Coderbuds makes that its own data contradicts, or a material omission. That definition distinguishes it cleanly from get-self-review-findings-tool (read) and record-self-review-fix-tool (fix tracking) without needing schema inspection.

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?

It gives an explicit positive trigger ('when your work in this repository or on production data shows Coderbuds' output is wrong in a way that will recur'), two explicit exclusions ('do not propose one-off bugs you can simply fix', 'do not propose a tidier wording of an open finding'), and names the prerequisite read tool to call first.

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