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

Goes well beyond the annotations: no test re-execution, gating on project opt-in, disclosure-only response when confirm_credit_spend is absent, shared daily cap, evidence reuse, worker credit/model checks, and the explicit caveat that queuing does not guarantee a draft. These are exactly the cost and side-effect facts an agent needs before spending the owner's money.

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?

Front-loaded with the purpose and the 'never reruns tests' boundary, and every clause carries real information. It reads as a semicolon-chained run-on, which slows parsing for such a dense set of caveats.

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 paid mutation with no output schema, the description covers cost gating, prerequisites, and the non-committal nature of queuing. What is missing is what a successful call actually returns (a request ID? a queued job reference?), which matters because there is no output schema to fall back on.

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%, so the baseline is already 3; the description earns more by explaining the behavioral contract of confirm_credit_spend (false/missing yields a disclosure with no queuing) rather than just restating it. run_id is clarified as relevant to historical failed runs, though project opt-in is a parameter-adjacent concept not tied to project_id explicitly.

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 ('paid request for a historical failed run or unavailable handoff') and immediately bounds it with 'never reruns tests', which separates it from trigger_framework_run and from get_framework_handoff. An agent can tell what this does and what it does not do without opening the 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 trigger condition is explicit: only for a historical failed run or an unavailable handoff, and only where the project has opted in and the owner has approved pricing. It does not name the sibling it supersedes (get_framework_handoff) outright, leaving the agent to infer that this is the fallback when the normal handoff is missing.

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