agentfarm_create_runQueues an authenticated asynchronous task. This can consume paid model capacity. Poll with agentfarm_get_run_status, then read agentfarm_get_run_result.
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | Task for the agent to complete. | |
| task_input | No | Optional JSON-compatible context or input data for the task. | |
| idempotency_key | No | Optional retry key; the same key and input return the original run. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses meaningful behavioral traits beyond the annotations: the task is asynchronous ('Queues'), requires authentication ('authenticated'), and can consume paid model capacity. These are significant facts an agent needs before invoking the tool, and none of them are present in the annotation booleans.
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, purposeful sentences: the first states the core action, the second warns about cost, and the third gives the follow-up workflow. There is no filler or redundant restating of the schema.
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?
The description is largely complete: it explains the async behavior, cost implications, and the correct next steps. The only gap is that it does not explicitly state what the create call returns (e.g., a run ID needed for polling), though that is reasonably implied by the polling instruction.
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 the schema already documents task, task_input, and idempotency_key. The description adds no additional parameter-level detail, but it is not required to compensate because the schema fully covers parameter semantics.
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?
The description uses a specific verb, 'Queues', and a clear resource, 'an authenticated asynchronous task', which matches the title 'Create a Sonnet 5 Agent run'. This clearly differentiates it from siblings like agentfarm_get_run_status, agentfarm_get_run_result, and agentfarm_cancel_run, which are all read or lifecycle operations.
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 gives a clear workflow: create the run, poll with agentfarm_get_run_status, then read with agentfarm_get_run_result. It does not explicitly state 'use this instead of X' or list when-not-to-use conditions, but the workflow context makes the intended usage unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool serves a distinct purpose: agent identity, task creation, status polling, and result retrieval. No overlaps exist.
Three tools follow verb_noun pattern (create_run, get_run_result, get_run_status) but agent_info uses noun_noun, creating a minor inconsistency.
Four tools perfectly cover the task lifecycle for an agent farm without excess or deficiency.
The set covers create, status, and result retrieval but lacks a cancel/delete tool, which would be a natural addition.