check

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

Annotations already cover read-only, non-destructive, open-world safety. The description adds genuinely new behavior: results are sorted by severity and pagination (offset/limit) is applied per engine, not globally, plus the ability to include likely false positives. That per-engine pagination detail is the kind of non-obvious trait annotations cannot 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?

One front-loaded summary sentence, then a compact per-argument list with no filler. Every line adds information; the only minor cost is the generic 'Args:' scaffolding.

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 7-parameter tool with no output schema, the description covers inputs well but says nothing about the shape of a returned finding or what 'per engine' means in practice. It is adequate to invoke the tool, but an agent cannot anticipate the response structure.

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 burden, and it does: all seven parameters get meaningful semantics (path defaults to the working directory, file is a glob or prefix like 'app/Http/**', offset/limit are per-engine, false_positives includes flagged items). Only 'name' and 'severity' rely on their enum values rather than prose.

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 states the resource precisely ('findings of one check') and adds two scoping traits (sorted by severity, paginated per engine), so an agent knows what comes back. However, the verb is implicit and the sibling tool 'audit' is never mentioned, so it cannot be distinguished from the alternative on the description alone.

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?

There is no when-to-use guidance, no statement of when to prefer this over 'audit', and no prerequisites or exclusions. The argument list implies usage but the agent must infer the selection criteria.

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