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

Beyond the readOnly/idempotent annotations, it discloses cost (free, keyless), that it moves no money and requires nothing to sign, and critically frames the meaning of its output ('no machine-checkable blockers never means the work happened or was good'). That interpretive caveat is exactly the kind of behavioral context annotations can't convey.

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 core purpose and the key caveats are front-loaded and earn their place. There is mild redundancy between 'Free, keyless, moves no money' and the closing 'Cost and signer: free and keyless, nothing to sign,' which repeats information rather than adding it.

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 an output schema present, annotations covering the safety profile, and full schema coverage, the description needn't explain returns. It completes the picture with the dry-run framing and the crucial output-interpretation caveat, leaving nothing an agent needs to call it correctly.

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?

With a single fully-specified parameter (100% schema coverage including nested package structure), the schema carries the semantic load, so the baseline is 4. The description adds no field-level detail beyond what the schema already documents.

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 and resource — a reproducible 'second read' of a 'work-evidence package you hold' — and enumerates exactly what it surfaces (missing evidence, impossible captures, checklist, artifact hash). This clearly separates it from siblings like verify_work or prepare_evidence_surface by scoping it to a dry-run review of a caller-supplied package.

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?

It gives clear timing guidance ('before it goes to the human who accepts it') and explicit exclusions (creates no order/receipt, never accepts or rejects). It does not name a specific alternative sibling to use instead, which keeps it just short of a 5.

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