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

Goes well beyond the annotations: discloses the exact relay endpoint, that the server holds no keys or funds, that the call is free with no gas, that signing is done by the user's own wallet or passkey, and what is returned. These are real operational traits (custody model, cost, trust boundary) not encoded in readOnlyHint/openWorldHint/idempotentHint/destructiveHint.

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-loads the action and the three inputs in the first sentence, which is the right structure. However, the closing sentence repeats 'free' and 'house never holds a key' already stated earlier ('Free with a valid signature', 'this server holds no keys'), so a little trimming is possible.

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 and full annotation coverage, the description supplies everything an agent needs: the upstream prepare step, the required payload provenance, the trust/cost model, and the relay target. No material gaps remain for a three-parameter submit tool.

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 100%, so the schema already documents all three parameters, including that bodyJson is the exact string from prepare_direct_offer and signature is personal_sign over MESSAGE_TO_SIGN. The description reinforces the 'UNCHANGED' constraint and the MESSAGE_TO_SIGN target but adds no new semantics, so the baseline of 3 applies.

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 ('Complete the offer') plus the exact resource and its place in a two-step flow ('step 2 of 2'), and names the sibling prepare_direct_offer as the source of the payload. An agent can distinguish this from submit_direct_settlement and the other submit_* tools without opening a schema.

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?

Explicitly frames the tool as the second half of a prepare/submit pair and instructs that BODY_JSON must come from prepare_direct_offer unchanged, which implies when to call it. It does not name exclusions or contrast with submit_direct_settlement, so it stops short of full when/when-not guidance.

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