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

With no annotations, the description carries the full burden of behavioral disclosure. It transparently states blocking behavior, terminal states, and timeout behavior. However, it does not disclose what happens on timeout (e.g., return value, error, or current status) or what the tool returns when the task settles.

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 short sentences with no filler. The core behavior, the recommended usage, and the expected duration are all front-loaded and concise.

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 there is no output schema and no annotations, the description should explain the return behavior and timeout results. It covers blocking semantics and timing well but leaves the caller guessing about what a successful or timed-out invocation returns.

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 for undocumented parameters. It only loosely references the timeout concept and does not explain task_id or timeout_seconds beyond what the schema constraints already show, making the parameters harder to reason about.

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 uses a specific verb and resource: 'Block until a task settles (succeeded/failed) or the timeout passes.' It clearly differentiates itself from get_task by framing this as a blocking wait rather than a polling call.

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?

It explicitly names get_task as the alternative and says this tool is 'Preferred over polling get_task in a loop,' giving clear usage direction. It also provides timing context ('Generation typically takes 10-60 seconds'), though it does not state edge cases such as when a caller should avoid waiting.

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