job_status

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

With no annotations, the description carries the full burden and does well: it discloses that cancel stops the job while the scene retains the changes the job already made, and routes the user to rollback for undo. It omits the exact return format/progress shape and any indication of whether polling is required, which keeps it out of the top band.

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?

Front-loads the tool's purpose and enumerates state outcomes compactly, then handles the job-id origin, the no-arg listing behavior, and cancellation/undo. Dense but each sentence carries information; no filler.

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 two-parameter, no-annotation, no-output-schema tool, the description covers purpose, both parameter behaviors, the lifecycle that produces job ids, and the cancel/rollback side effect. It is nearly complete, lacking only detail on the returned progress/result payload.

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 0% and parameters are bare (no descriptions), so the description must compensate. It does: `job` is defined by its absence (lists all session jobs) and `cancel=true` is defined as stopping the job. Both parameters gain meaning beyond the schema.

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 noun+behavior — reporting the state of a background job — and enumerates the possible outcomes (running/progress, done/result, failed/error). An agent can tell what it returns. It does not, however, differentiate itself from the sibling `status` tool, which is the one thing that could confuse selection.

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?

Explains the trigger condition: long tools that exceed their `wait` seconds return a job id, which you then poll here; omitting `job` lists all session jobs. It names the alternative `rollback` for undoing a canceled job's changes. No explicit when-not-to-use, but the context is clear.

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