Bounded existing job polling

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the bar is lower. The description nonetheless adds real behavioral detail beyond them: a bounded budget of 20 GETs, an explicit refusal to create/resubmit, and terminal-state semantics (completed/failed stop the poll; missing or unrecognised state stops as 'unknown'). That last rule in particular is nontrivial behavior an agent cannot get from the schema or annotations.

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 compact sentences with the core operation front-loaded before the constraints. No filler or restated boilerplate. It is dense rather than verbose, though the terminal-state rule and the polling budget are packed tightly enough that a reader must parse carefully.

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 and no nested objects, the description carries the return-shape burden, yet it only gestures at states (completed/failed/unknown) without describing what the poll actually yields or how partial/in-progress results are returned. Combined with the unexplained interval_ms and account parameters, it is adequate for a simple polling call but leaves meaningful gaps.

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% across 5 parameters, so the description must compensate. It does partially: the enumerated resource types explain the `resource` enum, and 'At most 20 GETs' echoes the max_polls ceiling of 20. But `uid`, `account`, `max_polls`, and `interval_ms` receive no direct explanation of format, default behavior, or backoff semantics, leaving roughly half the surface unstated.

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 ('Read only') and enumerates the exact resource types it covers (image, animation, batch, tool job, workflow run), which maps cleanly onto the `resource` enum. An agent can tell it is a read/poll operation on existing jobs. It does not, however, explicitly differentiate itself from siblings like get_image, get_batch, or get_tool_job, so the agent must infer that this is the polling variant.

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 (poll an existing job until it reaches a terminal state) and constrains it with 'At most 20 GETs, no create/resubmit', which tells the agent this is not a creation path. But it never names an alternative or states the condition for choosing this over the plain get_* siblings, leaving the when-to-use decision implicit.

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