Проверить ИИ-сервис

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

Beyond annotations (readOnlyHint=false, idempotentHint=false), the description discloses that this is a real request consuming limits and potentially costing money. It also mentions it shows 'reason for refusal,' indicating potential failures. These are valuable behavioral traits not captured in 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?

The description is two sentences long, front-loaded with the action and outcome, and the cost warning is a necessary caveat. Every sentence earns its place with no fluff or repetition.

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?

Given the simplicity of the tool (3 parameters, no nested objects, no output schema) and the strong annotations, the description covers the essential aspects: what it does, what it returns (response or error reason), and the cost/limit implications. It is complete for an agent to select and invoke it correctly.

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 100%, and each parameter (case, prompt, provider) already has a description. The tool description adds no additional parameter-level semantics, so it reaches the baseline but does not elevate it. It does not repeat or contradict schema information.

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 states a specific verb+resource: 'Sends a test replica and shows the model's response or reason for refusal.' This clearly distinguishes it from sibling tools like ai_list or ai_save, as it is about testing an AI service rather than managing configurations or listing services.

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 gives clear context: it sends a real request to the service and warns that it consumes limits and may cost money. This implies caution and informs when to use (testing a service) but does not explicitly name alternatives or exclusions. The cost warning is a useful usage guideline, though it could be more explicit about comparing to ai_list/ai_save.

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