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

Annotations already cover safety (readOnly=false, destructive=false, idempotent=false, openWorld=true), and the description adds genuinely new behavior: the output is an unsigned payload, the operation is non-custodial, and keys/preimages must never be sent. It does not explain that the payload must subsequently be signed and submitted, which would complete the picture.

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?

Short and front-loaded with the endpoint, which is good. But the middle sentence is dense internal jargon ('flop-htlc', 'hasStation.satisfyEscrow') that consumes space without informing an agent, while the actionable follow-up step is omitted.

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?

No output schema exists, so the description must explain the return value, yet it only cryptically gestures at an 'unsigned ... satisfiesEscrow' payload and never says what to do with it (sign and send via crew_submit_signed). For a three-parameter build tool with an undocumented claimId, the definition leaves too much for the agent to reconstruct.

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 only 33% — only 'from' is documented in the schema. The path notation ':id' hints that jobId is the target job, but claimId is never mentioned anywhere and its role in a payout is left entirely to guesswork, so the description fails to compensate for the coverage gap.

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?

Names the concrete endpoint (POST /jobs/:id/payout) and the resource (job payout), and the word 'unsigned' implicitly separates it from crew_submit_signed. The second sentence's jargon ('flop-htlc returns unsigned hasStation.satisfyEscrow') obscures rather than clarifies what is actually produced.

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?

'after verify' is the only usage signal, implying a prerequisite step exists but never naming the tool that performs it (crew_proof/crew_status). No explicit statement of when to prefer this over crew_submit_signed or other build tools, so routing must be inferred from the word 'unsigned'.

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