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

Adds substantial context beyond annotations: relays to POST /labor/work/:workId/settle/token, the server holds no keys/funds/tokens and reads the chain only, and there is no gas cost because the user's own wallet or passkey signs. It does not describe failure behavior for an invalid signature or whether the settlement becomes irreversible on-chain, which 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?

The core instruction is front-loaded and useful, but cost and key-custody facts are duplicated: 'this server holds no keys... and reads the chain only' is repeated as 'the house never holds a key', and 'Free with a valid signature' is restated as 'Cost and signer: free, no gas'. Trimming those repetitions would sharpen it.

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 mutating submission tool with annotations, full schema coverage and an output schema, this covers the workflow, custody model, cost, and what the settlement response contains. The main remaining gap is error/failure guidance for a rejected or invalid signature.

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 explains workId, bodyJson and signature. The description reinforces that bodyJson must be passed unchanged and ties it to prepare_token_settlement, but largely repeats the field documentation rather than adding format or validation rules. Baseline 3 is appropriate.

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 record', pass workId/bodyJson/signature) and identifies itself as step 2 of 2, which cleanly distinguishes it from prepare_token_settlement. An agent can tell exactly what this does without opening the 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 names the prerequisite tool and the exact artifact to carry forward ('BODY_JSON from prepare_token_settlement UNCHANGED', signature over MESSAGE_TO_SIGN). It stops short of stating when not to call (e.g., missing/expired signature), but for a chained submit tool this is clear, actionable context.

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