Wait for an asynchronous job to finish, up to 9 seconds, and return its current result; call again if it is still running.
Wait until a job finishes (at most timeout_seconds, default and limit 9) and return it as jobs.get does; call again while it is still running.
| Name | Required | Description | Default |
|---|---|---|---|
| job | Yes | Job id from the call that started it. | |
| timeout_seconds | No | Longest wait. |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description is free to spend its words on the behavior that matters: this call blocks up to a capped 9 seconds and must be re-invoked to keep waiting. It does not say what is returned if the job fails or if the wait expires, which is the remaining 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?
One sentence, front-loaded with the blocking wait, then the timeout cap, then the return contract, then the polling instruction. Every clause carries new information and nothing is repeated from 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?
Covers what it does, how long it waits, what it returns (by reference to jobs_get) and how to keep waiting — enough to call it correctly without an output schema. The terminal states (job failed, job vanished) are left unstated.
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 coverage is 100%, so the baseline would be 3, but the description adds the one thing the schema omits: that timeout_seconds defaults to 9 and that 9 is also the ceiling. It still doesn't explain what happens at timeout 0 or what the return looks like mid-run, but that is beyond the parameter scope.
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 verb and resource ('Wait until a job finishes') and immediately anchors the return shape to a named sibling ('return it as jobs.get does'), which distinguishes it from the plain jobs_get lookup. It stops short of naming the sibling as the non-blocking alternative, but the blocking-vs-snapshot distinction is still legible.
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 clause 'call again while it is still running' tells the agent exactly how to drive the tool — poll in a loop until the job completes. That is clear usage context, though it never states when to prefer jobs_get or agent_wait over this tool, so there is no explicit exclusion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.