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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds genuinely new behavior: a pending audit returns 'still running' rather than an error, nothing is charged for that, and failures explain what happened to the charge. It also discloses the public-vs-private auth model, which annotations do not cover.

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?

The core action and its states are front-loaded, and each clause (state handling, free/no-charge, auth model) carries real information. The em-dash-heavy packing makes it slightly dense, but no sentence is filler.

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?

There is no output schema, so the description carries the return contract — markdown digest with verdict, scores, top findings, and a report link — plus the non-error pending and failure cases and the auth requirement. That is everything an agent needs to call and interpret it.

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 the single `id` parameter is fully documented in the schema, including that it comes from the /report/{id} URL. The description only restates that it is a UUID lookup and adds no syntax or format detail beyond the schema, so baseline 3 applies.

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 (retrieve) and resource (a nittim audit) and pins the lookup key as a UUID. It also enumerates the possible return states (finished digest, still running, failed), which distinguishes it cleanly from creation siblings like audit_repo and audit_source.

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?

Gives clear usage context: use it with a UUID from a /report/{id} URL, it is free/uncharged, and it works for public repos without a key but requires the owning account's key for private ones. It does not name a sibling alternative or exclusion, so it falls short of a 5.

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