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

Annotations already declare readOnly, idempotent, non-destructive, closed-world. The description adds genuinely new facts beyond them: no bearer token is required and execution consumes prepaid run units. That auth-and-cost context is exactly what an agent needs and is not derivable from 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?

Two sentences, zero filler, front-loaded with the return payload followed by the important call-cost caveat. Every clause earns its place.

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?

Even without an output schema, the description enumerates what is returned, and it covers the two things an agent could get wrong here: whether it costs anything and whether auth is needed. Nothing material is missing for a parameterless metadata tool.

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, so there is nothing for the description to disambiguate; baseline is 4. The schema is empty and fully covered, and the description correctly does not waste words inventing arguments.

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 ('Returns') and resource ('this agent's identity') and enumerates the exact payload: per-task price, MCP endpoint, access URL. An agent can immediately distinguish this metadata call from the run-execution siblings like agentfarm_create_run.

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?

Clearly frames the tool as a metadata/introspection call that 'does not run the model,' implicitly routing the agent away from the run tools when it only needs identity/price/endpoint. It stops short of naming an explicit alternative or a triggering condition such as 'call this before creating a run'.

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