find_candidates

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

Despite readOnlyHint already declaring this is a read-only operation, the description adds important behavioral detail: all 24 proper rotations are considered, mirror readings are excluded, tolerances are 0.1 mm or 1%, unmatched values are flagged, and empty/truncated recognition is not treated as proof of absence. No contradictions 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?

The description is dense but each clause adds meaningful information about matching semantics, tolerance, rotations, and output handles. It opens with the main action before diving into qualifier and tolerance details.

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 complex geometric matching behavior, the description covers the crucial semantics: rotations, bounding-box-relative sides, tolerance, absence-handling, and feature-handle return. An output schema exists, so return details are not required; the one notable gap is the undocumented object_name parameter.

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 0%, so the description must explain parameters. It does explain qualifiers (axis, side, value_field) and stated_value semantics in detail, and kind is implied by the feature list, but object_name is never described. This is partial compensation, not complete.

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 names a specific verb ('List') and a concrete set of resources (hole, boss, polygonal boss, slot, chamfer, fillet), and specifies the return of exact @feature handles. It is clear enough to identify the tool's function, though it does not explicitly contrast with similar sibling finders like find_holes or find_bosses.

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?

There is no explicit statement about when to use find_candidates versus the many find_* siblings, nor any when-not-to-use guidance. The behaviour (qualifiers, tolerance, rotations) implies a measurement/candidate-matching use, but the agent is left to infer context.

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