Scan findings

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the description doesn't need to cover safety. It still adds real behavioral context: results are ordered most-severe-first, and false positives are excluded by default unless include_false_positives is true. The one omission is truncation behavior for limit (default 50) — nothing says whether output is capped or how totals are reported.

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?

Two sentences, no filler: the first leads with what is returned and in what order, the second covers the filtering controls and the default false-positive exclusion. The most decision-relevant facts (ordering, default exclusion) are front-loaded.

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?

An output schema exists, so return-field structure needn't be restated and the description appropriately focuses on ordering and filtering. Given a 4-parameter tool with 0% schema coverage, the only substantive gap is limit/pagination semantics; otherwise an agent has enough to call this correctly.

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 0%, so the description must carry the parameter burden. It explains severity (as a filter) and include_false_positives (default exclusion of false positives), and implies scan_id via 'of a completed scan', but the limit parameter is never mentioned, so an agent can't tell whether raising it retrieves more findings or whether results are paginated.

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) and its scope (of a completed scan) and enumerates the returned fields (severity, title, CWE, MASVS, CVSS, location, description), which is far more specific than the title 'Scan findings'. It implicitly distinguishes itself from get_scan/list_scans by dealing in findings rather than scan metadata, but never states that distinction explicitly.

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?

'Findings of a completed scan' establishes a precondition (the scan must be finished) and the severity filter implies when to narrow results. However, there is no explicit guidance on when to use this versus get_scan or wait_for_scan, and no statement about what to do if a scan is still running.

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