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

With no annotations, the description explains key behavioral traits: the job is async, results are cached per account by content hash, the force flag bypasses cache, and it requires 'audits:run' permission for API keys. This adds significant value beyond the input schema.

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 sentences are concise and front-loaded with the primary purpose. No unnecessary words, but could be slightly more structured for scanning.

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?

Given the tool's complexity (10 parameters, async behavior, no output schema), the description omits critical details: how to track the job (e.g., via rubrkit_poll_job), what the response looks like, and the meaning of missing parameters. This leaves the agent underinformed.

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?

Despite 0% schema description coverage, the description only explains the 'force' parameter (its CLI equivalent and effect). Nine other parameters (modelTier, rubricKey, etc.) are left unexplained, failing to compensate for the schema's lack of descriptions.

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 description clearly states 'Start an async audit job', using a specific verb-resource pair. It is distinguishable from sibling tools like rubrkit_list_audits or rubrkit_read_audit which only read, not create jobs.

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 description gives guidance on when to use the force flag ('to bypass the cache and run a fresh audit'), but does not indicate when to use this tool versus alternatives. Since no sibling tool starts an audit, the usage context is implied.

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