audit_config

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

No annotations are supplied, so the description carries the full burden. The audit verb and the enumerated read-only targets imply a non-destructive scan, and the cross-file scope is a genuine behavioral trait worth knowing, but the description never states that nothing is written, what permission or environment prerequisites exist, or 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?

Front-loaded with the core purpose, followed by the sibling exclusion and then an example — a sensible information order with essentially no filler. The parenthetical file list is dense but earns its place by making the scan surface concrete.

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 no annotations and no output schema, the description should carry more of the behavioral and result-shape burden. It tells the agent what to pass and what categories are checked, but says nothing about what a result looks like, whether findings include severity or file locations, or what the json format yields.

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 100% and both parameters are documented inline, so the baseline is 3. The example audit_config({path: '.'}) usefully demonstrates that path should be the project root, but the format parameter's effect (markdown vs json) receives no added meaning beyond the schema's one-word description.

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 (audit) plus the exact resource (application config files) and enumerates the concrete artifacts checked (next.config, middleware, .env, vercel.json) and the gap classes found (missing headers, unprotected routes, exposed secrets). It explicitly contrasts itself with the sibling guardvibe_doctor, so an agent can route between them without opening either schema.

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?

Provides an explicit exclusion ("NOT the same as guardvibe_doctor which checks AI host security") and a concrete invocation example, which gives clear usage context. It does not, however, position itself against the many other audit-adjacent siblings such as full_audit, check_project, or scan_config_change, so the agent still has to infer that boundary.

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