job_status

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

Goes well beyond the annotations (readOnly=false, destructive=false): it explains that cancel=true stops the job, that already-applied scene changes PERSIST, and that rollback is required to undo them. That is exactly the 'what survives/what gets destroyed' context the annotations cannot express, and it is consistent with them.

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?

Three sentences, front-loaded with the resource and its states, then the trigger condition, then the mutation/undo semantics. Every clause (including the named long-running tools) earns its place.

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 supplies the return-value shape (progress/result/error) itself, covers both parameters despite 0% schema coverage, and reconciles the mutation with the destructive=false annotation. Nothing needed to call it correctly is missing.

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%, so the description must carry both parameters — and it does: omitting `job` lists all jobs, and `cancel=true` stops the job. It does not state the expected format of the `job` id, a minor residual gap.

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 resource (background job) and enumerates the returned states (running/done/failed), so the agent knows exactly what this reports. It never explicitly distinguishes itself from the sibling `status`, which is the only real ambiguity in an otherwise clear statement.

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 the precise trigger condition (long tools like fit_to_reference/match_camera/bake_maps return a job id when they exceed `wait`), the no-argument behavior (lists all jobs), and routes the undo case to the `rollback` sibling. Nothing about when to reach for this tool is left to inference.

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