catia_audit_model

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

Annotations only declare readOnlyHint=true and openWorldHint=false. The description goes well beyond: it does not modify the document, ranks issues error>warning>info, returns a structured issue shape (code, where, message), supplies fix tool calls with args or a 'manual' fallback, and discloses 'not_checked' limits of the API (e.g. sketch degrees of freedom). This is rich behavioral disclosure for a read-only tool.

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?

Front-loaded with the core action and read-only guarantee, then dense but informative enumeration of checks and return shape. Every clause adds value (checks per Part vs Assembly, the fix/manual contract, not_checked). It is somewhat long as a single block but not padded.

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 output schema, the description carries the burden of describing returns, and it does so thoroughly (severity ranking, issue fields, fix tool+args, manual instruction, not_checked). For a complex audit tool this is complete enough for an agent to invoke and interpret results correctly.

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% with an enum on min_severity, so the schema already documents the parameter. The description adds meaning by explaining the severity ordering (error>warning>info), which is exactly the scale the min_severity filter operates on, giving the agent context beyond the raw enum.

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+resource+scope: 'Audit the ACTIVE document's tree WITHOUT modifying it.' This clearly distinguishes it from sibling tools like catia_get_tree (raw tree fetch), catia_drawing_check (drawing-specific), and catia_describe_model (description). An agent can tell what it does and what it doesn't.

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 read-only 'WITHOUT modifying it' constraint and the extensive list of what it checks give strong context for when to invoke it. It implies that remediation is a separate step via the returned 'fix' tool calls, but it never names a sibling as an alternative or gives explicit when-not-to-use guidance.

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