Create a generation (paid)

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

Despite annotations already declaring openWorldHint=true and destructiveHint=true, the description adds crucial operational details: requires confirmed=true, refuses otherwise, contacts no backend, and auto-generates an X-Idempotency-Key to prevent double-charging. This goes beyond generic hints and explains the concrete safeguards.

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 tight sentences: the first states the purpose, the second explains the confirmation guardrail, and the third covers idempotency. No fluff, front-loaded, and highly efficient.

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?

The description covers all key aspects: paid nature, confirmation requirement, byte-identical constraints, and idempotency. However, it does not mention the return value (e.g., generation ID) nor explicitly instruct to call deepy_estimate_generation first, though the sibling list implies this workflow.

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?

The input schema provides 100% coverage with detailed descriptions for every parameter, including byte-identical constraints and idempotencyKey behavior. The description's mention of 'byte-identical' and 'auto-generated idempotency key' mirrors existing schema text, so it adds little new parameter-level meaning.

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?

The description uses a specific verb ('Start') and resource ('generation'), and the word 'PAID' immediately distinguishes this from estimate, list, or get operations. It clearly states the tool's core purpose and differentiates from siblings like deepy_estimate_generation.

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?

The description clearly states the prerequisite (confirmed=true) and the behavior if not met (refuses, no backend). It also implies the need for a prior estimate via 'byte-identical to the estimate', but it does not explicitly name the estimate tool as the prerequisite or list when-not-to-use alternatives.

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