List the audit modules and codes

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so 'Makes no network requests' largely restates structured data. The genuinely additive details are that output includes one line per code and that the ids are only meaningful for audit_site; beyond that, nothing about result shape or caching is disclosed.

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 sentences with no filler, which is appropriately sized for a zero-arg discovery tool. But the middle sentence ('`target` is the up-front fetch of the page') is obscure and does not earn its place, leaving the reader to decode intended meaning.

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 an output schema present, return values need no explanation, and zero parameters keep the surface small. What is missing is a clear statement of where this fits in the workflow relative to audit_site and explain_finding, and the dangling `target` reference leaves an unresolved question about whether any input is expected.

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?

The schema has zero parameters, which would normally give a baseline of 4. However, the description backticks `target` as if it were an input, while the schema declares no properties at all — this invites an agent to hunt for a nonexistent argument. That ambiguity outweighs the zero-param baseline.

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 and resource: lists every audit module id with the issue codes it can report plus a one-line summary. It also names the sibling that consumes the ids (`audit_site`), which helps differentiate. The second sentence about `target` is cryptic and muddies rather than sharpens the purpose.

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?

The phrase 'the up-front fetch of the page' implicitly signals this is a discovery step to run before audit_site, and '(for audit_site `only`)' scopes the output's consumer. But there is no explicit 'use this when…' or exclusion versus explain_finding, and the wording is garbled enough that an agent must infer the workflow.

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