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

With no annotations, the description carries the full burden. It usefully discloses that the verdict is precomputed and signed and that each call costs $0.01 unless covered by a plan, but says nothing about auth requirements, behavior on a missing key, staleness, or what the signed payload contains.

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?

A single front-loaded sentence with a compact argument list and no filler. The pricing aside is relevant cost context rather than padding.

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 lookup tool with no output schema and no annotations, the description does not explain the returned verdict shape, failure behavior, or how it relates to verify_receipt. An agent would have to discover these by trial.

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 should compensate, but it only restates the three parameter names. It does not clarify that tree_hash is required while harness and version are optional, nor whether the key must match exactly.

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 resource, a precomputed signed verdict, and the composite key it is keyed on (tree_hash x harness x version). An agent can tell this is a cached lookup rather than a computation, which distinguishes it somewhat from verify_receipt, though no sibling is named.

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?

There is no statement of when to use this versus preopen_audit or verify_receipt, nor what to do when no precomputed verdict exists. The pricing note gives context but not routing guidance.

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