security_audit

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

No annotations are provided, so the description carries the full burden. It discloses one important trait, 'Read-only', but says nothing about cost/model spend, caching, per-attempt time budget, or the shape of the result. The schema's workdir description also states it reads nothing above the root and writes nothing, so 'Read-only' is partly redundant with structured data; the description adds a little but leaves the behavioral picture thin for an 11-parameter tool.

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 short telegraphic sentences: what it finds, where to use it, and the read-only guarantee, with the issue classes front-loaded. There is no filler. The fragmented list style trades a little readability for density, which keeps it just under a 5.

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 complex 11-parameter tool with 100% schema coverage and no output schema, the description covers purpose and when-to-use but omits anything about how it differs operationally from codex_review/gemini_review or what the agent gets back. Given the schema covers parameters fully and no output schema exists, the remaining gap is sibling differentiation, so an adequate-but-not-complete 3.

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 100%, so the schema already documents all 11 parameters thoroughly (tier semantics, workdir sandboxing, objective, checks). The description adds no syntax, format, or defaults beyond that. Baseline 3 is correct when the schema does the heavy lifting.

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?

It states a specific domain: finding exploitable security issues, and enumerates the classes it covers (injection, authz gaps, secrets, SSRF, path traversal, races, client-input trust). That is enough to distinguish it from the generic review siblings (codex_review, gemini_review) and the structural siblings (edge_cases, plan_critique) without naming them. It is a noun-phrase list rather than a clean verb+resource, but the purpose is unambiguous.

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?

It gives concrete triggers: use on auth, payments, user input, file paths, shell commands. That is a clear context-of-use. It stops short of explicit exclusions or naming the sibling to pick instead when the question is not security-relevant, so it is not a 5.

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