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

With no annotations, the description carries the full burden and discharges it: it discloses that polling never starts work, that sleep_ms is the single authoritative sleep value, that estimated_remaining_ms must never be used as a sleep duration, that status=cancelled is a user stop not to be resubmitted, and that _meta carries queue_position/queue_depth/queue_lane/estimated_start_ms for explaining waits.

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?

Dense and long, but the length is largely earned by the state-machine semantics (next_action vocabulary, queue metadata, anti-patterns) that an agent must follow. The mirror-vs-native constraint and prerequisite are front-loaded, though a couple of clauses (e.g., re-stating that next_action/sleep_ms are mirrored under _meta) are mildly 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?

An output schema exists, so return values needn't be enumerated, and the description even confirms 'The result is the same Task status document returned by native tasks/get.' Combined with the routing rules, prerequisites, and discouraged behaviors, an agent has everything needed to invoke and sequence this tool correctly.

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?

One required param with 0% schema description coverage, so the description must compensate, and it does: 'Prerequisite: task_id from the immediately preceding async submission' tells the agent exactly where the identifier comes from. It stops short of format specifics (e.g., string shape/length), so not a full 5.

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 names a specific verb+resource (retrieve the Task status document for a submitted async task) and explicitly frames itself as the 'tool-only client equivalent of native tasks/get.' It distinguishes itself from siblings tasks_result and tasks_cancel, telling the agent it is the polling/status read, not the result fetch or cancel.

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 states when to use it ('Use only when this mirror appears in tools/list'), when not to (Tasks-capable clients use tasks/get), the prerequisite (task_id from the immediately preceding async submission), and routes each next_action value to the correct follow-up call (sleep_and_poll, consume_result, stop_error). Exclusions and alternatives are explicit.

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