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

With no annotations, the description carries the full behavioral burden, and it does well: it discloses that the finding lands as 'proposed', that nothing happens until a person accepts it, and that only internal staff should use it. It does not describe failure modes or duplicate handling, but the persistence and review workflow is clearly conveyed.

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?

Every sentence earns its place: purpose and workflow first, then usage conditions and exclusions, then parameter semantics. The bolded rules are easy to scan and there is no filler.

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 6-parameter mutation tool with empty annotations and no output schema, the description is nearly complete: it explains what constitutes a finding, how to phrase the key fields, and what happens to the result. It is only missing explicit information about the return value or API behavior on success, which would make it fully self-contained.

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?

The schema already covers all six parameters, but the description adds real semantics for the two most important ones: it specifies that 'claim' must contain what Coderbuds says, what the data says, and why it matters, and that 'evidence' should be omitted rather than invented. This is meaningful guidance beyond the schema descriptions.

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 opens with a specific verb and object ('Propose a self-review finding') and defines the object as a contradiction between Coderbuds' output and the data it holds. It distinguishes itself from siblings by telling the agent to check get-self-review-findings first and by excluding mere re-wordings of open findings.

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 a crisp when-to-use condition: work showing recurring wrong output in a PR comment line, metric, or verdict. It also gives explicit when-not-to-use rules (one-off bugs, tidier wording) and points to an alternative tool to check for open findings.

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