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 adds meaningful behavioral context beyond the annotations: the task is asynchronous, requires authentication, and can consume paid model capacity. This is especially valuable for a mutation-like operation where cost and async behavior are critical for agent decision-making. No contradiction with annotations.
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?
The description is two concise sentences with no filler. It front-loads the core action, then adds a critical cost warning and a clear follow-up path. 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?
For a tool with no output schema, the description adequately explains the full lifecycle: creation, polling, and result retrieval. It also surfaces the cost and auth requirements in one short description. Combined with the complete parameter schema, the agent has everything needed to call this tool correctly.
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?
The input schema has 100% parameter description coverage, so the baseline is 3. The description itself does not add parameter-level detail beyond what the schema already provides, but the schema already sufficiently documents 'task', 'task_input', and 'idempotency_key'.
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 resource ('an authenticated asynchronous task'), clearly identifying the tool as the creation/queueing step. It also implicitly distinguishes from sibling tools by referencing the follow-up status and result tools, so an agent understands this is not the poll or read operation.
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 clearly states the intended workflow: queue a task, then poll with agentfarm_get_run_status, then read agentfarm_get_run_result. This gives clear context on when to use this tool relative to its siblings. It does not explicitly state when not to use it or mention alternative creation methods, but the workflow guidance is strong.
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 targets a distinct operation: agent metadata, create, cancel, status polling, and result retrieval. The status and result tools are clearly separated since one returns lifecycle state and the other returns final artifacts.
All tools share the agentfarm_ prefix and mostly follow a clear verb_object pattern (cancel_run, create_run, get_run_status, get_run_result). agentfarm_agent_info is a minor deviation because it uses a noun phrase rather than a verb, but it is still predictable and consistent with the overall style.
Five tools is well-scoped for an async run lifecycle: create, cancel, check status, fetch result, and inspect agent metadata. There is no unnecessary bloat or missing essential action.
The tool set covers the full async task lifecycle from creation through cancellation, status polling, and result retrieval. The agent info call rounds out the surface for discovering the agent's identity and pricing. No critical operations appear to be missing.