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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds meaningful context beyond them: unmeasured data comes back as TODO rather than a guess, and the call is free (no credit). That is exactly the kind of caveat annotations can't express.

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-loads the core purpose, then the three kinds, then the TODO caveat, the exclusivity constraint, and the cost note. Dense but every sentence carries information; minor nesting in the kind list is the only drag.

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 an output schema present, return values need not be described, and the description still covers artifact variants, TODO placeholders, the pre-commit check, parameter exclusivity, and cost. Referencing a needsHumanInput tool absent from the sibling list is the one loose end.

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 parameter definitions are already documented, but the description adds a constraint the schema does not enforce: 'Pass exactly one of report_id or domain_id', plus the report=page-scoped / domain=site-scoped mapping implied by the kinds.

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 ('Generate a file that fixes a deterministic finding') and enumerates the three artifact kinds with a short gloss for each, so an agent can tell exactly what it produces. It is clearly distinguishable from siblings like get_fix_plan or get_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?

Gives real usage context: use it for deterministic findings, check needsHumanInput before committing, and pass exactly one of report_id or domain_id. It doesn't explicitly name an alternative tool or a when-not-to-use condition, so it falls short of a 5.

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