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

Annotations already declare destructiveHint=true and idempotentHint=true, so the agent knows cancel is a destructive, repeatable operation. The description adds the anti-polling directive, which is useful context beyond annotations, but says nothing about what cancel does to the task result or about authorization/rate limits.

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 definition is brief and the high-value directive ('never poll') is front-loaded. The trailing example is ambiguous enough that it does not clearly earn 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?

There is no output schema, so the description should hint at what a 'get' returns (e.g., task state/progress), and it does not. Combined with the 0% parameter coverage, the agent has enough to call the tool but not enough to interpret results well.

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 carries the burden for both parameters. It only gestures at syntax with the cryptic 'Example: cancel taskId', never clarifying that action is a separate optional enum, what its default is, or how taskId is obtained.

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?

'Get or cancel one task' gives a specific verb and resource, and the tool is clearly the single-task status/cancel counterpart to the batch sibling wait_images. It is distinguishable from siblings, though it never names them.

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?

'never poll' supplies one real usage rule: call this rather than polling. However it does not say when to prefer wait_images, nor when to choose get vs cancel, so the guidance is implied rather than explicit.

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