catia_pocket

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

Annotations only declare safety flags (readOnly=false, destructive=false), so the description adds real value: it discloses that auto direction verifies material removal and flips if nothing was cut because CATIA's default side is unreliable. That is non-obvious behavior an agent cannot infer from the annotations or 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, front-loaded with the core action, then the direction caveat, then the limit enum. Dense and mostly waste-free, though the parenthetical '(Jusqu'à la suivante)' and '(proven live)' add flavor more than actionable content.

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?

For a 5-param mutation tool with no output schema and annotations covering the safety profile, the description covers the key behavioral pitfall (auto-direction flipping) and limit options. It leaves out error/precondition behavior (e.g. what happens with no sketch, or on failure), a minor gap.

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 80%, so the schema already documents most parameters. The description reinforces limit semantics (fixed depth, up_to_next, up_to_last/through) and the auto-direction behavior, but adds little for depth, name, or sketch_name beyond what the schema states, so baseline 3 holds.

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 and resource ('Create a Pocket (cut extrusion) from the last sketch'), and the parenthetical clarifies it removes material, which implicitly distinguishes it from catia_pad. It does not explicitly name the sibling it contrasts with (e.g. catia_pad or catia_hole), so it falls just short of full sibling differentiation.

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?

It describes how direction='auto' behaves and enumerates the limit modes, which implies when each applies, but never states when to choose a Pocket over sibling operations like catia_pad, catia_hole, or catia_groove, nor what prerequisites (active body, sketch present) must hold.

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