job_status

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

No annotations are provided, so the description carries the full burden. It usefully discloses the three terminal/transient states and that a 'last step' is returned, but says nothing about polling cadence, whether a finished job's payload is retrievable here, or retention/expiry of jobs.

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 resource and the returned states; the parenthetical example list is the only slightly expendable content. No filler or restatement of the name.

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 single-parameter status tool with no output schema and no annotations, the description covers the essentials of what is returned. It remains incomplete on the lifecycle question — how to move from status to actual results, and how long a job_id stays valid.

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% for the single job_id parameter, so the schema gives no meaning at all. The description compensates partially by explaining that job_id originates from a long tool call that passed the sync budget, but it does not describe the id's format or where to source it explicitly.

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?

Names a specific resource (a background job) and its verb (report state), and enumerates the possible states plus the last-step detail. It is clear what comes back, though it never contrasts itself with the sibling job_result, which covers the result-fetching counterpart.

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 description explains the trigger context well — jobs spawned by long tool calls that exceeded the sync budget — so an agent knows when a job_id exists. It stops short of stating when to prefer this over job_result or what to do after seeing 'finished', leaving the routing inference to the agent.

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