deploy.run

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

Adds significant behavioral context beyond annotations: fee held from credit balance, captured only after verification (failed free), automatic DNS creation conditional on CLOUDFLARE_API_TOKEN, and polling. No contradictions with annotations.

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?

6 sentences, each earning its place: purpose, preconditions, parameter usage, billing behavior, error handling, DNS setup, and post-call action. Front-loaded with core purpose, no redundancy.

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?

With 7 parameters, 2 required, 100% schema coverage, output schema present, and a detailed description covering error recovery, billing, DNS, and lifecycle, the tool definition is fully actionable for an AI agent.

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%, establishing a baseline of 3. The description adds workflow context for parameters like 'resources' (selection evidence) and 'outcome' (deployment objective), enhancing their purpose beyond basic schema descriptions.

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 ('provision') and resource ('the explicitly selected suggestion'), clearly stating the tool's role in deploying after user approval. It distinguishes itself from sibling tools like suggestions.generate by being the deployment step.

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 states when to call ('Never call before presenting options and receiving user approval') and provides detailed guidance on handling HTTP 402 (call billing.top_up and retry), referencing related tools, and instructing to poll deploy.status after accept.

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