check_airtight_path

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

No annotations are provided, so the description carries the full burden and does so: 'Inspection only: measures, returns no handle, mutates nothing' discloses the safety profile. It further explains the mechanism (both ports sealed with cap solids, negative-space void analysed) and the meaning of each status value, which is behavior an agent could not infer from the schema.

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?

Long but front-loaded: the purpose sentence comes first, then per-parameter and per-return-field blocks. Given 0% schema coverage and no output schema, the length is largely earned. The 'Returns a dict' block is dense but structured; only minor trimming (e.g. parenthetical elaborations) would be possible.

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 annotations, no output schema, and 0% param coverage, the description supplies everything an agent needs: inputs with formats and defaults, the capping/analysis method, the full return dict with field types and meanings, and the pass/fail semantics via `ok` and `status`. Nothing material is missing for correct invocation or interpretation.

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 fully: `handle` is the part to inspect; `inlet`/`outlet` are defined as rim-face references with the four accepted forms (f_* tag, 'FaceN', int, annotate_face role); `min_aperture_mm2` sets a bottleneck threshold with the 'almond slit' failure case; `pad_mm` documents its default formula. Each param gets meaning beyond the bare schema types.

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 precise verb+resource ('functional check for an enclosed-flow part') and names the exact question it answers (single connected void joining inlet to outlet). It explicitly distinguishes itself from the sibling `check_shape` — 'catches what check_shape cannot' — so an agent can route between them without opening either schema.

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 a clear selection rule against the closest sibling (`check_shape`) via the watertight-vs-flow-path distinction, and notes the tool is inspection-only. It does not enumerate when NOT to use it (e.g. open-channel or non-enclosed parts), leaving that to inference.

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