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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral facts: no bearer token needed, no model invocation, and that execution (elsewhere) consumes prepaid run units — relevant economic context an agent cannot get from the schema or 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 compact sentences with the return payload front-loaded and the no-cost/no-auth caveat following immediately; every clause carries information and nothing is repeated from annotations or schema.

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?

With no output schema, the description itself summarizes the returned fields (identity, price, endpoint, URL), and it covers the two things an agent would otherwise have to guess: auth requirements and whether calling it costs anything. Complete for a parameterless metadata call.

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 the baseline is 4; there is nothing for the schema to document and nothing the description needs to compensate for.

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 enumerates the exact resource payload: identity, per-task price, MCP endpoint, and access URL. This is readily distinguishable from the run-management siblings (create_run, cancel_run, get_run_status, get_run_result), which all operate on runs rather than on agent metadata.

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 clarifies the key selection condition versus execution tools by noting this call 'does not run the model' and 'does not require a bearer token', implying it is the pre-flight/lookup call before create_run. It stops short of explicitly naming create_run as the alternative when you want to actually execute, so it is clear context without full routing language.

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