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

Annotations only declare destructiveHint=true; the description earns its keep by explaining why (consumes fal credits when the model runs) and by disclosing the full return contract (request_id, response_url, status_url, cancel_url, queue_position) plus the underlying POST {queue}/{model_id} semantics. It stops short of explaining polling/cancel follow-up flow.

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?

Three dense sentences, front-loaded with the async contract, then the return shape, then the side effect and wire format. No filler and no restatement of the tool title.

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 two-parameter tool with no output schema and only a destructiveHint annotation, the description supplies everything the agent needs: async semantics, cost implication, documented return fields, and a pointer for discovering model-specific input fields.

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?

With 100% schema coverage the baseline is 3, but the description adds real mapping information: the body equals the model input and model_id is interpolated raw into a path segment. It also actively points to falai_get_model_schema as the way to discover the arbitrary per-model input fields, which the schema itself cannot enumerate.

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+resource (submit an inference request to the queue) and immediately differentiates its mode of operation: 'return immediately (async — does NOT wait for completion)'. That distinction separates it from the synchronous-sounding sibling falai_run_model without needing to open either 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 async/does-not-wait framing is a clear when-to-use signal, and it routes the agent to falai_get_model_schema for building the input object. It never explicitly names falai_run_model as the synchronous alternative, so the choose-between guidance is implied rather than stated.

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