verify_feature

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

With no annotations, the description carries the full burden and does well: it discloses that the tool does NOT raise on mismatch and that the caller must inspect `passed`, which is the critical behavioral trait. It also explains the two-tolerance pass/fail logic and the accepted handle types. It omits whether it requires an active document or prior volume state, so not quite complete.

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?

Front-loaded with a one-line summary, then failure examples, then parameter semantics, then the return shape. Dense but every block earns its place; the parameter list is slightly verbose but justified given 0% schema coverage.

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 verification tool with no output schema and 0% parameter coverage, the description supplies everything needed: the return keys ({passed, message, actual_delta_mm3, expected_delta_mm3, ratio, previous_volume_mm3, current_volume_mm3, handle, name}), the non-raising contract, and full parameter meaning.

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: every one of the four parameters is explained with semantics and defaults beyond the schema — handle accepted types, signed sign convention for expected_delta_mm3, relative tolerance default 0.05, abs_tolerance default 0.01, and the OR-combination rule.

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+resource: 'Compare a feature's actual volume change against an expected signed delta.' This is clearly distinct from sibling measurement tools like mass_properties or check_shape, and the units (mm³) and the signed-delta concept make the operation unambiguous.

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 trigger ('Run after each subtractive/additive operation to catch silent failures') with three concrete failure scenarios (Pocket under-cut on curved surface, Hole outside body, Cut with non-intersecting Tool). It does not name alternative verification tools (check_shape, verify_intent, bounding_box) or state when *not* to use it, so it falls short of full routing guidance.

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