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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower. The description adds genuinely non-obvious behavior: no bearer token required for this call, and the billing distinction that only execution consumes prepaid run units. It stops short of describing response shape or any rate/caching behavior.

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. The returned fields are front-loaded and the caveats (no model run, no token, billing) follow immediately after.

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?

For a zero-param read-only metadata tool with no output schema, the description covers what is returned plus the auth and billing quirks an agent needs. A minor gap remains around response format/timestamp freshness, but nothing essential for correct invocation is missing.

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 and the schema is empty with additionalProperties false, so there is nothing for the description to disambiguate. Baseline 4 applies for a no-argument tool.

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 contents: identity, per-task price, MCP endpoint, and access URL. This is trivially distinguishable from the run-lifecycle siblings (create/cancel/status/result), which the agent can rule out without opening any schema.

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 explains the preconditions for calling it ('does not run the model and does not require a bearer token') and contrasts that with execution, which 'consumes prepaid run units'. That implies this is the cheap metadata lookup to perform before agentfarm_create_run, but it never names that alternative explicitly.

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