catia_prepare_geometry

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

The description states 'Safe to call repeatedly (idempotent) and that already-cached items are skipped', but the annotations declare idempotentHint=false. An agent deciding whether to retry this call gets directly conflicting signals. Otherwise the description is rich (cache mechanism, screen-reload cost, error reporting with closest-element distance), but the direct conflict with the annotation dominates.

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 action and its scope, followed by the cost rationale, the input convention, and error behavior. Every sentence carries information, though the explanation of CATIA window open/search/close and screen reload is somewhat verbose for the value it adds over 'this is slow per-element'.

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 a single parameter, full schema coverage and no output schema, the description covers the important ground: pre-constraint timing, caching, repeat-call behavior, and failure reporting (wrong point + distance of nearest element). It does not describe the success return value or the shape of the cached result, a minor gap given no output schema exists.

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 already 100%: the nested 'element' object fully documents face_point/axis_point/edge_point/plane and the part-coordinate convention. The description adds planning semantics the schema does not ('one item per (component, element) you will use in constraints') and reinforces the catia_list_faces workflow, but repeats part of the schema hint.

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?

Stated as a specific verb+resource ('resolve ALL the geometry designations an assembly will need') with an explicit scope qualifier ('in ONE pass, before adding constraints'). It is clearly distinguishable from the sibling constraint tools (catia_coincidence_constraint etc.) and from the listing tools (catia_list_faces), which it positions as the companion used to find points.

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 context: call this before adding constraints, because per-constraint designation costs ~1 s each and flickers the screen. It also points to catia_list_faces for discovering the points/axes to pass in. It stops short of naming an alternative tool or an explicit when-not-to-call condition, so it is not a full 5.

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