Compare CRUMB files under the Unity profile

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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description adds meaningful behavioral context: GUID-matched comparison, specific difference categories (exact bytes, modeled equivalence, root changes, component changes, unverified payload signatures), and explicit exclusions. This goes beyond what annotations provide and sets clear output constraints. No contradiction.

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 two sentences, front-loaded with the core action and scope ('Read-only, GUID-matched comparison'), and the second sentence efficiently enumerates what it distinguishes and what it omits. Every word adds value.

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?

The description gives a strong overview of the tool's behavior and output boundaries, and an output schema is present so return values are documented elsewhere. However, given the tool has 10 parameters and 60% lack schema descriptions, a brief mention of view modes, pagination, or topology options would improve completeness, but the provided overview is still adequate for basic understanding.

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?

The schema has only 40% parameter description coverage (baselinePath, candidatePath, expectedBaselineDigest, expectedCandidateDigest). The tool description does not explain any parameter semantics, leaving view, limit, cursor, topologyMode, includeGeometry, and compatibilityProfile without contextual guidance. Given the low schema coverage, the description was expected to compensate but does not mention any parameter.

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 clearly specifies a comparison tool ('Compare CRUMB files') with a particular scope: baseline vs candidate .cru under crumb.unity/1.3.5. It lists specific output categories (exact bytes, modeled equivalence, root/component changes, payload signatures) that distinguish it from sibling tools like crumb_inspect_design or crumb_validate_design.

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?

The description gives clear context: use for read-only, GUID-matched comparison of two CRUMB design files under a specific compatibility profile. It does not explicitly name alternatives or state when not to use it, but the purpose is unambiguous and the exclusions (no raw XML, firmware, EEPROM, thumbnails) help set expectations.

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