Test AI provider

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds real behavioral context beyond that: it records latency and errors, results are read via get_ai_status, and calls against API-key-billing providers are refused. What a refusal actually returns is left unstated, keeping it from a 5.

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?

Two compact sentences with zero filler; the core action leads and the important refusal constraint follows immediately. Every clause carries information an agent needs.

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 one-parameter probe with no output schema, the description is nearly complete: it explains the action, the recorded outcome, and where to read results (get_ai_status). The only minor gap is what an agent sees when a provider is refused.

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?

With a single parameter and 100% schema description coverage, including an enum of providers, the schema does the documentation work. The description adds no provider-specific semantics beyond what the enum already conveys, so the baseline 3 applies.

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?

States a specific verb and resource ('Send a tiny test prompt through a provider') plus the side effect ('record latency / errors'), and explicitly points to get_ai_status for the results. An agent can distinguish it from the sibling get_ai_status without opening either schema.

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?

Gives a clear context for use (probing a provider and seeing status) and an explicit exclusion: 'Refused for providers that bill an API key; the user runs those tests in the app.' It does not enumerate alternatives beyond get_ai_status, but the when/when-not framing is well covered.

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