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

No annotations exist, so the description carries the full burden and does substantial work: it discloses that no transaction or gas is required, that the replacement key is returned exactly once, and that the old key is invalidated — a genuinely irreversible side effect. It stops short of permissions/authorization requirements, error behaviors, or idempotency, which is what keeps it from a 5.

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?

Three sentences, front-loaded with the action and mechanism, then the cost note, then the critical consequence-and-storage warning. No sentence is filler; the ordering matches the order an agent needs the information.

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 credential-mutating tool with no annotations and no output schema, the definition covers ordering, cost, one-time secret return, and key invalidation — the essentials. It leaves out the response shape beyond 'the replacement key', failure/retry handling for a stale or mismatched challenge, and whether the signing wallet must match the challenge's wallet.

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% — the schema only has regex patterns and a uuid format, no prose. The description compensates for the hardest parameter by specifying that `signature` must be the EIP-191 signature of the exact message from the challenge tool, which is the main source of misuse. `challengeId` and `wallet` are only implicitly covered (challenge ID comes from the challenge call, wallet is the merchant wallet), so it doesn't fully compensate.

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 ('Rotate a lost merchant API key') plus the exact mechanism (EIP-191 signature). It names the prerequisite sibling create_merchant_credential_rotation_challenge, but never names the closest alternative, complete_merchant_credential_rotation_transaction, so the agent must infer the split from the passing phrase 'needs no transaction or gas.'

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?

'Rotate a lost merchant API key' gives the triggering condition, and the reference to 'the exact message returned by create_merchant_credential_rotation_challenge' makes the required call ordering explicit. What's missing is an explicit exclusion or failure case, e.g. what to do if the challenge expired or if the agent should prefer the transaction-based path in some situation.

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