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

Annotations already cover the read-only, idempotent safety profile, and the description goes well beyond them: it documents the next_action control contract, the meaning of status=cancelled, the queue-related _meta fields, and warns that estimated_start_ms is advisory rather than a wait time. That is exactly the behavioral context structured fields cannot carry.

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?

Front-loaded with the key routing fact and free of filler, but the sentence enumerating _meta queue fields edges into output documentation that the existing output schema already covers.

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?

For a polling tool with an output schema and full annotation coverage, this description supplies everything needed to call it correctly and interpret the result contract: next_action semantics, cancellation meaning, and queue-state caveats.

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% and the description only references 'a task_id' without stating its format or origin (e.g. where the id comes from, how it relates to tasks/list output). The single parameter is near self-evident, but the description does not 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?

States a precise verb and resource: 'Returns the Task status document for a task_id.' It also distinguishes itself from the sibling tasks_result by assigning that tool to the consume_result branch, so an agent can route between them without inspecting schemas.

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?

Gives explicit conditional routing via next_action: sleep_and_poll means wait sleep_ms then call tasks_get again, consume_result means one tasks_result call, stop_error means stop. It further clarifies that status=cancelled means the user stopped it and that polling never starts work, closing off the most likely misuse.

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