Verify Feature

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

Annotations declare readOnlyHint=true and no destructive intent, and the description reinforces that it 'Does NOT raise on mismatch' and returns detailed result fields. This adds behavioral context beyond annotations: no exception behavior, signed-delta convention, dual-tolerance pass logic (EITHER tolerance satisfied), and a complete return payload. Slight deduction because it doesn't state whether it modifies model state (though readOnlyHint implies it doesn't) or whether it requires a recompute/update before running.

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 opening line states the purpose, the second line gives the usage trigger and examples, then parameter semantics are front-loaded before result behavior. Every sentence earns its place: no filler, and the signed-delta warning is placed inline with the parameter it modifies.

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?

Output schema is absent, so the description correctly enumerates the full return object ({passed, message, actual_delta_mm3, expected_delta_mm3, ratio, previous_volume_mm3, current_volume_mm3, handle, name}) and tells the agent how to act on it (inspect passed to decide whether to abort). The sign convention, tolerance fallback, and failure examples cover all usage decisions. The tool is verification-only with no side effects, so nothing else is needed.

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% and the schema only has bare names/types, so the description carries the full burden. It explains handle as accepting both PartDesign features and Part::Cut, defines expected_delta_mm3 as SIGNED with sign semantics (subtractive negative, additive positive), explains tolerance as relative with default, and explains abs_tolerance as fallback for tiny magnitudes with EITHER/OR pass logic. This fully compensates for the 0% schema coverage.

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 states a specific verb ('Compare') and resource ('a feature's actual volume change against an expected signed delta'), and specifies exact failure modes (under-cut Pocket, Hole drilled outside body, Cut whose Tool didn't intersect Base). This clearly distinguishes it from verification siblings like verify_performance, verify_intent, verify_contract, and baseline_verify.

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?

Explicitly says when to run: 'Run after each subtractive/additive operation to catch silent failures' and gives concrete example scenarios. It doesn't explicitly name an alternative tool, but the sibling list contains no other volume-delta verification tool; the recommended trigger context is sufficient. It also tells the agent to inspect `passed` rather than rely on exceptions, which is actionable guidance.

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