record_roundtrip_evidence

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

With no annotations provided, the description carries the full burden and reveals key behaviors: it writes metadata, returns written=true only after both files verify, preserves authority=user_supplied, and cannot grant high trust. It does not detail the sidecar format or filesystem effects, but the core side effects and safety limits are disclosed.

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 compact, two sentences, with front-loaded purpose and no redundant phrasing. Each clause adds specific behavioral or trust information, earning a high score for efficiency and clarity.

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 covers trust, verification, and purpose, but leaves gaps around the mandatory 'path' parameter and how to construct the evidence object. The output schema may clarify return values, and the input schema has nested descriptions, but the top-level semantics remain under-specified, making the tool only moderately complete.

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 top-level parameters 'path' and 'evidence' have no descriptions in the schema (coverage 0%). The description does not explain what 'path' is for or how to structure the 'evidence' object beyond vague references to 'evidence manifest' and 'both files.' Although nested schema definitions exist, the description fails to add meaningful parameter-level guidance.

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 states the tool writes an evidence manifest and provenance sidecar, explicitly refraining from design bytes. It distinguishes from siblings like validate_roundtrip_evidence by focusing on recording rather than validating, and from design-editing tools via the 'not design bytes' clause.

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 useful context about when to use it: for user-supplied evidence, with a guarantee it never grants high trust. It does not explicitly name alternatives or exclusions, but the 'not design bytes' hints at separation from design modification tools, and the trust warning guides when not to rely on it.

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