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

Annotations already cover readOnly/idempotent/non-destructive, but the description adds context they cannot express: the cost model ('Free: does not use a credit'), the stability guarantee of ids across re-scans, and the per-finding 'apply' vs propose policy governing whether an agent may act unattended. These are material behavioral traits for an agent deciding whether and how often to call it.

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?

Dense and largely waste-free, with the operating constraint and alternatives present, but it opens with a definitional sentence about findings rather than the action itself and runs long in a single block. Nothing is redundant enough to cut outright, though it could be split for scanability.

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 read-only, two-parameter list tool with a full output schema, the description supplies everything else an agent needs: the error case, the cost implication, and the follow-up tools. Return value details are correctly left to the output schema.

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, but the description adds the mutual-exclusivity rule and its failure mode, which the schema only hints at with 'Omit if you pass...'. It clarifies which source each id maps to (one page vs latest site analysis) in a way the schema field descriptions do not fully frame.

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 names the resource ('findings'), defines it concretely ('the fix list keyed by rule'), and explicitly separates it from the sibling get_report ('Use get_report instead if you only need scores'). An agent can distinguish this from get_report, verify_findings and get_fix_plan without opening any schema.

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 states the exact invocation constraint ('Pass exactly one of report_id ... or domain_id ... otherwise it returns an error'), names a substitution for a neighboring need (get_report for scores), and lists the downstream tools that consume the returned ids (verify_findings, update_finding, get_artifact). This is explicit when-to-use and when-not-to-use guidance.

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