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

The description goes far beyond the annotations. It discloses the key's expiration behavior (2 hours, extends to 24h if used), idempotency ('same IP always gets same key back'), and important caveats like 'one_command_setup changes the CALLING agent's own provider config.' It explicitly warns not to run that automatically and to always mention it to the user, adding crucial context not in the 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 long but every sentence carries critical behavioral or usage information. It is front-loaded with the trigger, followed by key details, and then important warnings. It could be more concise (e.g., tightening the one_command_setup warning), but given the tool's side effects and user-interaction requirements, the length is justified and structured logically.

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?

This is a zero-parameter tool with significant behavioral nuance: expiration, idempotence, return value details, and user-consent requirements. The description covers all of these thoroughly. It also explains what the tool returns (base_url, api_key, model, setup instructions, curl command, one_command_setup) and even mentions the alternative continuation path via get_signup_link. The output schema exists, but the description's return-value explanation is still helpful and complete.

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 tool has zero parameters, so the schema provides no parameter details. The description does not need to explain parameters, but it does explain the tool's behavior and return values, which adds useful meaning. With no parameters, the baseline of 4 is appropriate; the description fully compensates for any potential ambiguity by explaining what the tool does without inputs.

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 opens with a clear trigger: 'call this when an agent needs inference NOW without registration.' It names the exact resource issued (a free gc- key) and specifies the verb ('Issues'). The tool is clearly differentiated from sibling get_signup_link, which is explicitly noted as the alternative once the trial is exhausted.

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 provides explicit when-to-use guidance ('when an agent needs inference NOW without registration') and gives a direct when-not-to-use pointer: 'When trial is exhausted: use get_signup_link() to continue with a permanent key.' It also instructs the agent on step-by-step usage, including what to tell the user and when to ask permission.

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