inspect_query

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

With no annotations the description carries the full burden and mostly does: it discloses AND semantics for filters, kind-scoped filter applicability, that mismatched combos or min>max raise INVALID_PARAMS, units (mm, mm²), result format ('brief descriptions with refs'), truncation semantics, and the default scope of all visible bodies. It omits execution cost/volume limits beyond the scope hint and doesn't state read-only nature explicitly (only implied by 'find').

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?

Purpose is front-loaded in the first clause, followed by contract rules and then a compact example block. The examples occupy roughly half the text but each demonstrates a distinct useful filter combination, so they earn their space; a little trimming of the return-shape sentence into the examples would be tighter.

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 19-parameter, annotation-free tool with no output schema, the description supplies the error model, default scope, units, truncation behavior and return shape. Remaining gaps are secondary: relationship of returned `ref`s to other tools and the meaning of ordering/sorting options.

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?

At 63% schema coverage the description adds real meaning: the kind-gating rule for filters (surface_type needs kind="face"), the AND-of-all-filters rule, units for length/area/radius, and example pairings that show how filters combine (surface_type+normal, curve_type+direction, radius range for holes). It leaves `order`, `axis`, and `sort_by` semantics largely to the schema, so it doesn't fully close the coverage gap.

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 ('find') and resource ('faces, edges, vertices or bodies') plus the defining scope: by geometry filters. The phrase 'instead of writing code' implicitly contrasts it with execute_python, making the tool's role in the sibling set unmistakable.

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?

Gives concrete invocation patterns via five worked examples and a real usage rule ('On large models narrow `scope` to one body'), plus a constraint that filters are ANDed. It does not explicitly route the agent away from siblings like inspect_tree, inspect_describe or inspect_bounding_box, so no exclusion guidance.

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