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

Annotations already declare readOnlyHint=true, so safety is covered, but the description adds genuinely useful behavioral context beyond them: the response is metadata only and explicitly excludes secret values, and it names the underlying REST call (GET /v1/api-tokens). It stops short of describing pagination or the shape of the metadata.

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 short sentences, front-loaded with the action and the key caveat about secret values, followed by the endpoint. No filler.

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?

There is no output schema, so the description carries some burden for return values; 'metadata only, not secret values' handles the most important agent concern. It could go slightly further by naming the metadata fields returned, but for a zero-param list tool this is nearly 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 takes zero parameters, which is the baseline-4 case; there is no parameter semantics to clarify. The description correctly implies no filtering or input is needed.

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 ('List the account's API tokens') and immediately scopes the result ('metadata only, not secret values'). It is trivially distinguishable from siblings like deepinfra_list_models, deepinfra_list_deployments, and deepinfra_list_invoices.

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?

Usage is implied by the name and the zero-parameter shape: there is nothing to configure, so calling it to enumerate tokens is self-evident. However, the description offers no explicit when-to-use framing or reference to a sibling alternative (e.g. how it relates to deepinfra_get_account).

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