audit

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

Annotations already provide readOnlyHint, openWorldHint, and destructiveHint. The description adds behavioral detail about surface detection and fan-out logic. No contradictions. The description does not explicitly state return format or side effects beyond what annotations convey, but that is acceptable given the annotations.

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 two sentences. The first sentence is somewhat long but effectively communicates key behaviors. It uses bold and em dash for emphasis. Could be slightly more concise, but no wasted words.

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, no output schema, no return value description), the description provides an adequate high-level overview. However, it lacks details on what the tool returns (e.g., list of findings, results format), which would help an agent understand the tool's full output.

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 description coverage is 100%, so baseline is 3. The description adds moderate value by noting that 'project' is for taste binding and 'intent' for optional focus. This helps parameter understanding but is not extensive; most meaning is already in the schema.

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 it runs all applicable Raven audits for a target, includes surface detection and fan-out behavior. It also explicitly tells the agent to use this instead of choosing individual audit_* tools, effectively distinguishing it from the large sibling set of specific audit tools.

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 explicitly says 'Use this instead of choosing individual audit_* tools,' providing clear guidance on when to use this tool vs. siblings. It also mentions passing 'project' for taste binding. However, it does not explicitly state when not to use it or list alternative specific audit tools for narrow use cases.

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