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

With no annotations, the description carries the burden and does well: 'Nothing is signed or sent' clearly marks this as a non-destructive dry-run/plan step, and it discloses the fee model (1% fee, min 0.01) and devnet program id. It stops short of describing return format or prerequisites for the fee payment.

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 purpose and the 'unsigned / nothing sent' constraint are front-loaded, and the sentence count is small. Slightly dense with parenthetical fee and devnet asides, but every clause carries 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 plan-generation tool with no output schema and an opaque nested body at 0% coverage, the description explains the outcome and safety profile but leaves the request body's required fields undocumented. Adequate but incomplete on the input contract.

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, a nested object, at 0% schema description coverage. The description only says 'body is the /v1/settle request body,' which names the endpoint but gives no field-level structure for a nested object whose keys the agent must construct. This is a real gap, not merely a repetition of the schema.

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+resource: produces the unsigned settlement plan of one paid call via POST /v1/settle, and enumerates the plan's contents (job id, terms, calls[] with signers). It's clearly distinct from generic settlement siblings, though it doesn't name a specific alternative tool.

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?

No explicit when-to-use or when-not guidance, and no sibling alternatives named. The phrase 'via:"us" names our JudgeAdapter as the evaluator' implies a configuration choice but doesn't tell the agent when to pick this tool over taifoon_grid_settlement or taifoon_judge_compose.

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