identity_audit

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

With no annotations, the description carries the behavioral burden. The verb 'Audit' implies a read-only analysis and the parenthetical defines what is being detected. Still, it does not disclose whether the tool returns a list of violations, a report, or errors, and it does not specify side effects.

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 description is one tight sentence that front-loads the action and object and adds a useful clarifying parenthetical. There is no filler or redundancy.

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?

Because there is no output schema and no annotations, the description should at least state what the audit produces so an agent can interpret the result. It does not, leaving the tool's return contract underspecified.

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 provides 0% description coverage, and the description only repeats 'identity TOML' rather than explaining the expected format. An agent is left to infer whether identity_toml should be raw TOML content, a path, or something else.

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 names a specific action ('Audit'), a specific resource ('an identity TOML'), and a concrete objective (find coherence violations/contradictory signals). This clearly separates identity_audit from sibling identity_generate, which creates identities rather than validating them.

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 usage context is implied: call this when an identity TOML needs validation. However, the description does not explicitly state when to prefer this tool over identity_generate or other siblings, nor does it mention exclusions or preconditions.

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