pro_validate_design

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

Annotations already cover read-only, idempotent, non-destructive, closed-world, so the description earns credit for what it adds: the guarantee that it never rebuilds, saves, activates, or changes selection, and especially the result tri-state semantics — "ok means every check completed; passed means all conditions hold. Unknown is never pass." That distinction between completion and satisfaction, and the fail-closed treatment of unknown values, is not inferable from the annotations and is the key thing an agent must know to interpret results correctly.

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?

Four short sentences, front-loaded with the core purpose and check kinds, then constraints, then result semantics. No filler and no repetition of schema 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?

With no output schema, the description does the right thing by defining ok and passed and by warning that unknown never passes, and it flags the units/tolerance requirement. However, for a tool whose real complexity lives in a 128-item assertion array with five discriminated kinds and a summary/full result_view switch, the description leaves the assertion composition rules and the effect of result_view unexplained, so an agent still has to reverse-engineer much of the call shape from the schema.

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 carries the full burden and it only partially discharges it: "Requires explicit units and tolerances" usefully signals that unit and abs_tolerance are mandatory, but nothing explains the min/max versus expected exclusivity, the role of id, axis, component_a/component_b, document_path, or result_view. The oneOf structure is mechanically self-documenting, but the semantics of choosing a bound versus a point value are left to inference.

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 ("Check") and resource (assertion checks against the active saved model) and enumerates the five check kinds: dimension, mass, volume, axis-aligned size, and top-level part-pair distance. This cleanly separates it from sibling measurement tools like measure_distance, get_mass_properties, and get_bounding_box, which return values rather than validate against declared requirements.

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?

The enumerated check kinds and the phrase "explicit ... requirements" make clear this is the validation path rather than a query path, and "on the active saved model" plus "Requires explicit units and tolerances" sets a precondition. It stops short of naming alternatives (e.g., "use get_mass_properties to read a value instead") or stating exclusions, so the routing is implied rather than explicit.

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