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

With no annotations, the description does valuable disclosure work: a five-minute TTL, wallet binding, two proof modes (gas-free EIP-191 or zero-USDC Base transaction), and a custody guarantee ('402Mob never signs for it'). It omits whether re-issuing invalidates a prior challenge, any rate limits, and what the challenge object contains, which matters for an unannotated mutation-adjacent tool.

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 purpose, then the returned artifact, then the trust model. No filler and no restatement of the tool name.

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 single-parameter operation-start tool with no output schema, the description covers purpose, lifetime, binding, and proof options. It stops short of connecting the agent to the named completion siblings or describing the challenge payload, which is the remaining gap.

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?

One parameter with 0% schema description coverage, so the description must carry the load. 'Wallet-bound challenge' explains the role of the wallet argument (the challenge is tied to that address), but the required 0x-address format and the consequence of a mismatched wallet are left entirely to the schema pattern.

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: 'Begin recovery of a lost merchant API key,' and clarifies that this only issues a challenge rather than completing recovery. It distinguishes itself from the complete_merchant_credential_rotation_* siblings by describing only the challenge-issuance step, though it never names those follow-up tools.

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?

Gives clear triggering context ('lost merchant API key') and implies this is the first step before the wallet signs or submits. It does not explicitly name the sibling completion tools or state when to prefer enrollment-style challenges instead, so the routing is inferable rather than spelled out.

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