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?
Beyond the annotations, the description discloses that the task is authenticated, asynchronous, and can consume paid model capacity. It also communicates the expected lifecycle (queue, poll, read), which is valuable context not available from the annotations or schema.
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 sentences with the core action first and the cost/usage context second. It avoids filler, states the most important operational facts, and is well front-loaded.
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 an async creation tool with no output schema, this description covers the key operational facts: queue, auth, cost, and the follow-up polling/reading workflow using named siblings. The only minor omission is an explicit statement of what create_run returns (e.g., a run identifier), though this is strongly implied by the polling instructions.
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 thoroughly. The description does not add parameter-specific meaning beyond what the schema provides, so the baseline score of 3 applies.
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') with a clear resource ('an authenticated asynchronous task') and immediately distinguishes the tool from its siblings by naming the polling and result-reading tools. An agent can tell this creates/runs a task rather than inspecting or canceling it.
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 explicitly names agentfarm_get_run_status and agentfarm_get_run_result and ties them to the post-creation workflow ('Poll with..., then read...'). This gives the agent a clear sequence and identifies which sibling tools are used after creation.
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 addresses a completely distinct concern: identity/metadata, creating a run, fetching status, and fetching results. There is no overlap or ambiguity in their purposes.
The names follow a clear agentfarm_ prefix pattern, with three using verb_noun (create_run, get_run_result, get_run_status). 'agent_info' is a minor deviation as it lacks an explicit verb, but the pattern remains predictable.
Four tools is an appropriate scope for a simple asynchronous task runner. Each tool has a clear role, and no unnecessary tools exist.
The core lifecycle of create, status, and result is covered completely. A cancel operation or listing runs could be added but is not essential for the server's apparent purpose.