Check a background job

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new operational facts: the returned status set, elapsed time, live child-process count, and a 30-minute post-settlement retention window. It also explains the non-obvious semantic that a client timeout does not stop the underlying work, which is exactly the kind of behavior an agent cannot infer from the 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?

Four sentences, front-loaded with the action, then the rationale, then return contents, then retention. Every sentence carries distinct information and nothing is repeated from the schema or annotations.

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?

With no output schema, the description correctly carries the return-value burden by enumerating the status values and describing what accompanies them. For a one-parameter read tool, the retention window and timeout semantics close the remaining gaps an agent would need.

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% and the single jobId parameter is already documented there as 'the jobId returned when the job was started with async:true.' The description restates the async:true provenance but adds no format, lifecycle, or error semantics beyond the schema, so the baseline 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?

States a specific verb and resource ('Poll a background job started with async:true') and immediately scopes it to async-started jobs, which cleanly separates it from job_cancel and the synchronous plan/run siblings. An agent can tell what this returns (running/done/failed/cancelled plus timing and child-process counts) without opening anything else.

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?

Gives a clear condition for use ('started with async:true') and a rationale that functions as a when-to-use rule: polling is the only way to retain a long compile after a client timeout. It stops short of naming job_cancel as the alternative for stopping work, so the routing is implied rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.