catia_gsd_plane

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

Annotations are all false, providing essentially no behavioral disclosure, so the description carries the burden. It correctly states this is a creation operation (aligning with readOnlyHint=false) and lists the construction modes, but does not disclose side effects such as whether a new element is added to the active geoset, whether references are required for certain modes, or what failure conditions exist. No contradiction with 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?

Three sentences, zero fluff, with the core purpose front-loaded and the mode list compactly formatted. The final motivational sentence is slightly optional but earns its place by clarifying the tool's role. A tight, well-ordered definition.

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 tool with 10 parameters and 5 distinct modes, the description is reasonably complete but leaves gaps: it doesn't explicitly state that most modes require a reference token, that reference defaults to 'xy', or how the reverse parameter interacts with offset mode. The mode-to-parameter mapping is implied rather than spelled out, which could trip up an agent on required-argument assembly.

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 baseline is 3, but the description adds real value by mapping each mode to its governing parameters (offset→offset/reference, three_points→points, normal_to_curve→point/reference, equation→equation, angle→angle/reference). This mode-to-parameter linkage is not present in the individual schema field descriptions and helps an agent assemble correct arguments.

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 ('Create') plus a specific resource ('construction plane'), then enumerates all five modes with their defining inputs. The closing sentence explains the practical role of construction planes, distinguishing this tool from geometry-creation siblings like catia_gsd_point, catia_gsd_line, and catia_gsd_spline.

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?

Each mode names its required inputs ('offset' from an existing plane, 'three_points', 'normal_to_curve' at a point, 'equation' from ax+by+cz=d, 'angle' rotated about an axis), giving clear context for when each variant applies. The final sentence gives situational guidance ('when no face is in the right place'). It does not explicitly name alternative tools or list exclusions, but the mode breakdown is enough to route an agent correctly.

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