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

Goes well beyond the single destructiveHint annotation: it discloses credit consumption, the polling loop, and — most valuably — that a wait-budget timeout returns a { status, request_id, status_url, note } object rather than an error, which prevents the agent from mis-handling a normal outcome as a failure.

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 tight sentences, front-loaded with the core behavior and followed by the credit cost and the timeout contract. No filler.

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?

No output schema exists, and the description covers the non-obvious timeout return shape and names where the eventual result comes from. The success payload itself ('the result') is left generic, but with 100% schema coverage on inputs this is close to complete.

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 description coverage is 100%, including the 300s cap on max_wait_seconds and the default poll interval, so the schema carries parameter meaning. The description adds only the informal phrase 'wait budget', which is baseline-equivalent.

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?

Names a specific behavior chain (submit → poll until COMPLETED → return result) rather than just 'run model', and the word 'Convenience' tells the agent this is the synchronous wrapper. It is clearly distinguishable from sibling falai_submit_request (submit only) and the polling siblings.

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?

Explicitly routes the agent on the non-completion path: keep polling with falai_get_request_status / falai_get_request_result. However it never states the inverse condition (when to prefer falai_submit_request for long jobs), so the when-not guidance is partial.

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