woodstitch_start_eval

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

The description goes well beyond the annotations: it discloses real monetary spend, irreversibility once listeners begin, the hard ceiling mechanism via max_total_usd, the over_max refusal path, metered billing from the first judgement, and the pause-rather-than-overspend behavior. The only gap is that idempotentHint=false is never addressed, so the agent gets no guidance on retry safety for a costly call.

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 action and the money warning are front-loaded in the first sentence, followed by precondition, parameter semantics, and billing model in a logical order. Every sentence carries distinct operational information with no filler.

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 costly, open-world mutation with no output schema, the description covers the critical safety and sequencing context an agent needs. It stops short of explaining what the call returns on success or the role of quote_id and idempotency_key, which leaves some operational detail to inference.

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 0%, so the description must carry parameter meaning, and it does so thoroughly for user_confirmed_amount_usd — explaining it is transmitted as max_total_usd and acts as the spending ceiling. However, eval_id, quote_id, and idempotency_key receive no explanation at all, leaving half the parameters undocumented.

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?

"START an evaluation" is a specific verb plus resource, and the surrounding text makes clear this is the execution step that follows quoting, not a listing or creation tool. An agent can distinguish it from woodstitch_create_eval and woodstitch_cancel_eval without opening any 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?

Explicit when-to-use is given: only after the user has seen the total from woodstitch_create_eval and explicitly agreed. It also names the consequence of skipping that step (API refuses with over_max), so the sequencing requirement is unambiguous.

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