audit_repo

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

No annotations are supplied, so the description bears the full burden. It implies a non-mutating analysis that returns a report and enumerates the findings, but never explicitly states it writes nothing, what format the report takes, or whether it is expensive to run on a large repo.

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?

A single dense sentence whose list of findings is front-loaded and each item carries information. The colon-list construction is slightly awkward as the opening clause lacks a verb, but no wording is wasted.

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, no output schema, and no parameters, the description is the only source of information. It describes what the report covers, which is its main job, but omits the report's form (text vs. structured data) and any cost or side-effect expectations.

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 tool takes zero parameters, so the schema leaves nothing to explain; the baseline of 4 applies. The description correctly scopes the tool to an implicit whole-repository target rather than suggesting any selection inputs.

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 enumeration of report contents (rules/risks, hot spots, empty groups, unreachable code, blind spots) makes clear this is a repo-wide audit against .readfirst/map.json, which distinguishes it from narrower siblings like check_map. However, the description opens with a noun fragment rather than a verb, so the action itself is only implied by the tool name.

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?

Explicitly states when to invoke it: 'Use it before larger work, or to decide what to add to the map.' That is clear context for a pre-work audit. It does not name when to prefer check_map or read_list instead, so the routing among siblings is left to inference.

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