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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the bar is lower, yet the description still adds real value by warning that the call can consume paid model capacity and requires authentication. It does not explain that creation returns a run identifier needed for polling, which is the one behavioral gap.

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 short sentences, zero filler, with the core action and the cost/auth caveat front-loaded before the follow-up chain. Every sentence earns its place.

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 compensates by naming the status and result tools an agent must call next, and by flagging cost and auth. It would be fully complete if it noted that the run identifier returned by this call is what feeds those follow-ups.

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%, so all three parameters (task, task_input, idempotency_key) are already documented in the schema; the description adds no parameter-level detail. Baseline 3 is appropriate when structured fields carry the load.

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 action and resource: queues an asynchronous agent run, with the 'authenticated' qualifier signalling auth requirements. It's clear what the tool does, though it never explicitly frames itself as the entry point vs. the sibling poll/read tools beyond naming them in sequence.

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?

Gives a concrete follow-up workflow: poll with agentfarm_get_run_status, then read agentfarm_get_run_result. That's actionable routing. It stops short of when-not-to-use guidance (e.g. don't re-create a run when an idempotency key already returned one).

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