catia_describe_model

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

Annotations only declare readOnlyHint and openWorldHint, and the description goes well beyond them: it confirms no document mutation, discloses the 'opaque' fallback with replay.complete=false and 'nothing is guessed', and lists precise coverage limits (patterns, shell, draft, thickness, surfaces). This is the honest behavioral envelope an agent needs before trusting a spec-driven replay.

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 scope, then organized by CATPart / CATProduct / Limits / side effects. Dense and slightly long, but nearly every clause carries distinct information (units, file names, opaque handling) rather than restating the name.

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 must carry the return-value burden, and it does: it enumerates the spec contents per document type, states units, and explains the opaque/replay.complete mechanism. An agent has everything needed to call it and interpret the result.

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%, so the baseline is 3, but the description adds value the schema does not: it names the concrete artifacts written ('<name>_spec.json', '<name>_replay.py') and clarifies that files are written to output_dir regardless of the include_* flags. That extra artifact-level detail lifts it above baseline.

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 ('reverse-engineer') and resource ('the ACTIVE document') and then enumerates exactly what is produced for CATPart versus CATProduct. This clearly separates it from siblings like catia_get_tree, catia_audit_model, and catia_measure_model, which the agent can rule out without opening schemas.

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 strong usage context ('without modifying it', active document only, output_dir to persist artifacts) and an explicit limits section naming what is described vs opaque. It does not name an alternative sibling or state when-not-to-use, so it stops 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.