product

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

Annotations only declare readOnlyHint=false, but the description adds substantial behavioral context: honest verified/unsupported capability matrix, structured capability errors without stable selection, material rendering reported only when backend-verified, and review verdicts independent from geometry/STEP validity. These disclosures go far beyond structured metadata and are not contradicted by the 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?

The description is organized as a front-loaded summary followed by a compact bullet-style list of operations with inline annotations. Every line adds information and there is no filler or repetition. The length is appropriate for a multi-operation dispatcher.

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 complex dispatcher with 7 parameters, no output schema, and no enums, the description covers the operation inventory, several key data formats, and critical caveats (authority, verification, module_reservation). Remaining gaps include exact return shapes and semantics for operations like query_edges_by_semantic_role and review_summary, but overall it is substantially complete.

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?

With 0% schema description coverage, the description compensates by documenting operation names and data payloads for several operations (create_feature data fields, set_motion axis/angle/limits/clearance, render_view orientations and visual_style). However, some operations lack parameter detail, and common fields like doc_id, lease_token, and idempotency_key are not explained, leaving partial compensation.

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 clearly identifies the product domain ('Parametric consumer-product features, motion screening, views, and reviews') and enumerates specific operations, distinguishing it from sibling tools by domain. However, it is a multi-operation dispatcher rather than a single verb+resource, so it lacks the precision of a focused tool description.

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 provides explicit guidance for specific cases: USB cutouts require supplier-controlled or physically measured authority, and concept dimensions must use module_reservation instead. It does not offer a broad when-to-use/when-not-to-use statement, but the operation list and these exclusions give clear contextual usage signals.

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