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

Annotations already declare readOnly/no-destructive, so the safety profile is covered. The description adds real behavioral context that annotations cannot: the call is non-blocking and returns a 'bounded not-ready snapshot' rather than waiting. It stops short of saying what the snapshot contains or whether repeated calls are idempotent.

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 primary return behavior and followed by the fallback. Nothing redundant.

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?

Output schema exists, so return values needn't be explained. However, 'bounded not-ready snapshot' is undefined and the relationship to the sibling status/artifact/events tools is left unstated — for a polling tool in a dense family, that leaves a meaningful gap.

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% — task_id carries only format/pattern, no prose. The description says nothing about what task_id is (presumably an id from agent_task_list or a prior agent_task_start), so it fails to compensate for the coverage gap.

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?

Specific verb+resource ('Return the task result') with scope qualifier ('when ready'). It implicitly separates itself from siblings like agent_task_status and agent_task_artifact by returning the result payload itself, but never names those siblings explicitly.

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?

'without blocking on the agent' conveys the intended polling pattern and implies repeated calls are acceptable, but there is no explicit guidance on when to prefer agent_task_status or agent_task_artifact, nor any polling cadence or backoff advice.

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