Queue a read-only research job and receive its metadata immediately, enabling parallel execution while the primary agent continues its work.
Queue one controlled research job and return immediately with its job metadata.
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | ||
| timeout | No | ||
| scope_paths | No | ||
| output_schema | No | ||
| worker_profile | Yes | ||
| evidence_budget | No | medium |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds a meaningful behavioral detail beyond annotations: the tool 'return[s] immediately' rather than waiting for job completion. Annotations already signal non-read-only and non-destructive behavior, so the description does not need to restate that, but it also does not mention limits, validation failures, or side effects.
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 a single front-loaded sentence with no wasted words. It loses a point because the word 'controlled' is vague and does little to clarify behavior, but overall it is appropriately compact.
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 six parameters, no schema-description coverage, and no explicit sibling routing, this is too sparse to support correct invocation. The output schema covers the return shape, so that part is fine, but the agent is left guessing about parameter semantics and lifecycle context.
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 0%, and the description mentions none of the six parameters. It does not clarify what task, worker_profile, timeout, scope_paths, output_schema, or evidence_budget mean or how they interact, placing the entire burden on parameter names.
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 ('Queue') and resource ('one controlled research job'), and states the outcome ('return immediately with its job metadata'). It distinguishes from sibling start_jobs by explicitly limiting to one job, though it doesn't name the sibling directly.
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?
There is an implied usage context: use this to launch a single job and get its metadata right away. However, it does not state when to prefer start_jobs for multiple jobs, or mention that status and results are retrieved via get_job/get_result. No alternatives or exclusions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.