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

Annotations already declare readOnlyHint=true, destructiveHint=false, so the safety profile is covered. The description adds real value beyond them: cost is zero ('Free'), status=completed does not mean success so resultStatus must be read, and REDIS_URL governs cross-replica visibility with optional webhooks. It stops short of stating idempotency or polling cadence, so not a 5.

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?

Extremely front-loaded: the verb-resource-purpose lands in the first clause, then cost, then the critical status caveat. The telegraphic style ('Free.', 'webhook optional.') packs density but borders on cryptic for a reader unfamiliar with the deployment.

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-shape explanation is rightly omitted. The description still covers the two things the schema cannot: that completed ≠ success, and that resultStatus enumerates outcomes (suggest|need_input|verified|error|…). For a one-parameter read tool this is close to complete; the trailing ellipsis leaves the status set slightly open.

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 coverage is 100% and the schema already documents runId as the UUID returned when async:true, so baseline would be 3. The description adds provenance by naming the four producer tools that mint a runId, which helps an agent validate it has the right kind of identifier.

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 specific verb (poll) and the exact resource (async run identified by runId), and enumerates the four sibling tools that produce such runs (solve_task, run_playbook, run_workflow, verify_task). An agent can immediately distinguish this from job_status or check_submit without opening the schema.

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?

The condition for use is clear: poll when a task was started with async:true, and it names which producer tools those are. It also flags 'webhook optional' as the alternative delivery path, though it does not explicitly say when to prefer a webhook over polling or how often to poll.

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