job

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

No annotations are provided, so the description carries full burden. It discloses that it is a polling operation, returns status, progress, and result, and supports incremental updates via `since`. However, it does not mention error handling, potential server load from frequent polling, or whether the job is automatically cleaned up after completion. The behavioral traits are partially disclosed but not comprehensive.

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?

The description is a single, tightly packed sentence that front-loads the core action ('Poll a job') and then lists the key information returned. Every word contributes to understanding, with no filler or redundancy. It is appropriately sized for the tool's simplicity.

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?

Given the tool has a single required parameter and an output schema that likely describes the result structure, the description covers the essentials: it tells the agent what it does and what it returns. However, it doesn't describe polling frequency recommendations or how to interpret status values. The output schema might cover return values, but the description remains incomplete for edge cases like job errors or completion behavior, which could matter for an agent deciding when to poll.

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 compensate. It mentions `since` as a progress line filter, but does not explain the format of `job_id` or the semantics of `since` beyond 'progress lines after.' The default of 0 is in the schema, but the description doesn't clarify that it starts from the beginning. Overall, the description adds some insight but not enough to fully cover the parameters, so baseline 3 is appropriate.

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?

The description clearly states the tool polls a job and specifies what it returns: status, progress lines after `since`, and the result when done. This distinguishes it from sibling tools like `apply` or `cancel`, though it doesn't explicitly name alternatives. The resource (`job`) is clear and the verb `poll` is specific.

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 implies usage: it is for checking ongoing job status, with the `since` parameter for incremental progress. However, it does not state when not to use it or mention alternative tools (e.g., maybe `monitor` for real-time status). It gives clear context but lacks explicit exclusions or comparisons.

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