List findings

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and 'Read-only' merely repeats that. The description does add genuinely new behavioral context: the default run selection, the result ordering ('worst first'), and the kinds of records returned.

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 tight sentences, front-loaded with the read-only constraint, then scop; no filler and every clause carries information.

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 4-parameter, read-only query tool with no output schema, the description covers what is returned and in what order. It omits limit/pagination behavior and filtering semantics, which an agent would still need to infer from the 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 75%, so most parameters are already documented, including the run default which the description merely restates. The description adds no format or syntax detail for `severity`, `limit`, or how `project` refs/hashes are accepted.

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 clear verb+resource ('list findings') and defines the content precisely: failed API tests and website scan findings from a run. It implicitly distinguishes findings (problems within a run) from the sibling list_issues/get_issue, though it never names those alternatives 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?

Usage context is implied by 'default the latest finished one' and the run-scoped framing, but there is no explicit when-to-use guidance, no exclusion of list_issues, and no pointer to get_finding for single-item retrieval.

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