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

Annotations already mark this as a non-read-only, non-idempotent create operation. The description adds critical behavior beyond annotations: the token is returned exactly once, cannot be read back, and cannot make approval requests itself, which strongly informs how the agent should handle the result.

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 compact, front-loaded with the action, and uses the remaining space only for high-value constraints: what the token can do, what it cannot do, and the one-time visibility of the returned token.

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 usefully explains the return behavior: the answer carries the token exactly once and it cannot be read back. Combined with annotations and the fully documented single parameter, an agent has enough information to call and handle this tool 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 coverage is 100%, and the only parameter is already documented in the schema as the agent slug from list_agents. The description does not add any parameter-level meaning beyond what the schema provides, so the baseline score of 3 is appropriate.

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 and resource: creating a provisioner token for a service agent. It also explains what the token enables (a fleet or platform creating agent instances with their own credentials), distinguishing it from nearby actions like creating an agent instance directly.

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?

It gives clear context for when this tool is appropriate: when a fleet or platform needs to create instances of the agent on its own through the Agent Approval Protocol. It also states a key limitation (the token cannot make approval requests itself), though it does not explicitly name alternatives or exclusions.

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