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

The description adds genuinely useful behavior — free, no gas, signed by the person's own wallet or passkey, the house never holds a key, and the tool returns a targetUrl. But it asserts 'Re-submitting for the same packet returns the surface you already hold,' which describes idempotent semantics while the annotations declare idempotentHint=false. That conflict undercuts the behavioral contract the annotations are meant to provide.

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?

Front-loaded with the action and its inputs, then the chain to prepare_claim, then cost/signer notes. It is dense but nearly every clause carries information; only the trailing 'Cost and signer:' fragment is slightly redundant with 'Free, always' earlier in the text.

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 only two required params, full schema coverage, and an output schema available, the description covers what an agent needs: inputs, source of inputs, cost/auth model, and the next step. The one gap is the unresolved idempotency behavior on retries, which matters for an agent recovering from a failed call.

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 coverage is already 100%, so the baseline is 3. The description earns more by stressing that bodyJson must be passed UNCHANGED and that signature is the wallet's output over MESSAGE_TO_SIGN, which conveys the integrity requirement the field names alone do not.

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 verb and resource ('Complete the reservation') and ties it explicitly to step 1, prepare_evidence_surface, so an agent knows the ordering. It does not, however, distinguish this from the very similar sibling submit_evidence_write, which an agent must disambiguate on its own.

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?

Sequencing guidance is explicit: use it after prepare_evidence_surface produces BODY_JSON and a wallet signature over MESSAGE_TO_SIGN, and pass the resulting targetUrl to prepare_claim. It also covers the re-submission case. What is missing is any statement of when NOT to use it (e.g., versus submit_evidence_write).

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