check_skill

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

Annotations only provide readOnlyHint=true, and the description meaningfully extends this with 'No new charges,' concrete retry timing, and a conditional recovery rule. This gives the agent operational expectations beyond the structured annotation.

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 compact sentences, front-loaded with the core read behavior and side-effect note, followed by precise polling and recovery rules. No filler; the closing instruction about resource links adds actionable output guidance.

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?

Even without an output schema, the description covers what the response should surface ('Show completed resource links'), how to poll, when to stop polling, and how to handle retryable versus non-retryable failures. The remaining gap is explicit parameter guidance, already penalized separately.

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 description coverage is 0%, and the description never names or explains the two parameters, skill and requestId. It implies a request context via 'retry_request, with its exact parameters,' but does not clarify that requestId identifies the operation or how skill selects the resource, leaving the agent to rely solely on field names and enum values.

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?

Description states a specific verb ('Read') and resource ('skill images, partial failures and refund states'), and clarifies the operation has no side effects ('No new charges'). It does not explicitly contrast with sibling check_generation, but the skill-specific wording makes the tool's role clear.

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?

Provides explicit polling instructions: 'wait afterSeconds before polling (normally 10s)' and 'recover only when it says retry_request, with its exact parameters.' It also directly handles when-not-to-poll by stating that payment/auth/input failures and daily limits require a different action instead of polling.

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