pentest_add_finding

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

No annotations are supplied, so the description carries the full behavioral burden and does not meet it. It does not say where the finding is persisted, whether it requires an active engagement, whether duplicates are merged, whether the call is idempotent, or what is returned on success. Only the mutation intent is inferable from the verb.

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?

A single front-loaded sentence with no filler and the severity scale parenthetically attached to where it is useful. It is efficient rather than padded, though the extreme brevity leaves the rest of the tool undocumented.

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 10 parameters, no annotations, no output schema, and 0% schema description coverage, this tool needs substantially more prose than one sentence. The severity enum is the one useful addition; nothing explains the evidence/CVSS/CVE fields or how the finding relates to engagement state and later reporting.

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 0% across 10 parameters, and the description only documents the allowed severity values — which is valuable because the schema defines severity as a bare string with no enum. The other nine parameters (cve, cwe, cvss, target, evidence, description, recommendation, tool, title) get no meaning, format, or required/optional guidance beyond their names.

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 uses a specific verb plus resource ("Record a ... finding") and is distinguishable from siblings like pentest_list_findings and pentest_report. It does not explicitly name those alternatives, but the write-vs-read distinction is evident from the name/verb pairing.

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?

The word "verified" implies a precondition — record only findings you have confirmed, not raw observations — which is a genuine usage hint. However, there is no guidance on when to use this versus pentest_report, pentest_list_findings, or the scanner tools that surface candidate findings, and no mention of prerequisites such as a loaded engagement.

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