Add Primitive

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

Beyond the annotations (readOnly=false, destructive=false), the description discloses important behaviors: the difference between FreeCAD's internal Name and the display label, the effect on list_objects, bom_extract, and drawing/manifest layers, the default-label behavior treated as an unnamed generic solid by BOM/designation checks, and the returned handle's role in later boolean_op calls.

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?

The description is front-loaded with its one-sentence purpose, followed by dense parameter explanations and a return-value contract. The longer name/label discussion is justified because it prevents a subtle misuse around FreeCAD Name stability and BOM labeling, with no redundant restatement of schema defaults.

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 seven parameters, no enums, and no output schema, the description is complete: it defines the kind vocabulary, per-kind dimension usage, placement units/format, naming semantics and downstream consequences, and the exact return shape including how the handle is used in subsequent boolean_op calls.

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 0%, so the description must compensate, and it does. It explains the kind values, which parameters each kind uses (box uses w/d/h, cylinder uses r/h, sphere uses r), that placement is an optional [x, y, z] mm translation, and the precise meaning and side effects of the name parameter.

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?

The description states a specific action and resource: 'Add a primitive to the active document,' then enumerates the exact supported primitive kinds (box, cylinder, sphere). This clearly distinguishes add_primitive from the many add_* sibling tools such as add_gear, add_bearing, or add_fastener.

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 gives clear operational context: it targets the active document, supports optional placement and naming, and tells which dimension parameters apply to each kind. It does not explicitly name alternatives or state when not to use it, but the kind enumeration effectively scopes selection and no exclusions are necessary.

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