Estimate a deployment

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

Annotations already declare readOnlyHint/idempotentHint/non-destructive; the description reinforces that and adds real behavioral detail: it returns warnings for known failure modes (VRAM, non-Blackwell, insufficient credits, no idle hosts) and computes one-timeout-window credit cost. This is more than the annotations alone provide.

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 dense sentences, front-loaded with the key concept 'Dry run' and a clear behavioral distinction, then specifics and a next-action recommendation. No wasted words or repetition of schema content.

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 complex 9-parameter tool with no output schema, the description conveys what is returned (cost + warnings) and the side-effect-free nature of the call. It slightly under-specifies how strategy/schedule affect the estimate for non-SIMPLE strategies, but the schema's strategy descriptions and the tool's pre-flight role make it adequate.

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 has 100% parameter description coverage and documents all defaults/enums, so the schema does the heavy lifting. The description only adds high-level references to template/variant, GPU, and timeout window, which is helpful but not necessary because each parameter is already fully described.

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 names a specific verb ('resolve', 'validate', 'return the cost'), resource (deployment plan) and outcome (credits for one timeout window plus warnings). It explicitly contrasts with create_deployment ('Nothing is created'), so an agent can distinguish it from its sibling.

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?

'Call this before create_deployment and show the user the cost' is an explicit when-to-use instruction with the relevant alternative named. 'Dry run' and 'validate the plan' also signal it is the pre-flight planning tool rather than a mutating action.

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