review_security

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

With no annotations provided, the description carries the full burden and does well on the trust dimension: it explicitly promises that secret file contents are never read or returned, and it bounds its own coverage by disclaiming a full audit. It leaves unstated whether the operation is read-only and how findings are surfaced.

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?

Three sentences, all load-bearing: scope first, trust guarantee second, limitation third. No filler and no repetition of the tool name.

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 scanner with no output schema and a zero-coverage input schema, the description covers scope and data-handling but says nothing about the shape or volume of results (how findings are listed, whether severity is included). It is adequate but not complete for an agent deciding how to consume the output.

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% and none of the three parameters (path, limit, offset) are mentioned in the description. The names are conventional, but nothing clarifies that path defaults to the current directory or that limit/offset paginate findings, so the description does not compensate for the coverage gap.

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 specific verb ('Check') and enumerates the exact classes of findings it produces (credential-shaped values, dynamic code execution, raw HTML insertion, backend risks), so an agent knows this is a static security scan. It partially distinguishes itself from review_backend by scoping to 'selected backend risks', but never names the sibling 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 is implied by the enumerated check categories, and there is one useful exclusion ('This is not a full security audit'). However, it never says when to prefer this over scan_project, analyze_code, or review_backend, which overlap heavily with a security-scanning tool.

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