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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so safety is covered. The description adds behavioral context beyond annotations: polling until terminal state or timeout, return fields (status, err_msg, poll_count, elapsed_ms), result preview behavior, and the intended workflow with sibling tools.

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?

The description is well structured with front-loaded purpose and labeled sections (WHEN TO USE, WHEN NOT TO USE, RETURNS, WORKFLOW). It is somewhat long, and the Chinese trigger sentence is broad and not specifically tied to polling, while the WHEN NOT TO USE section contains vague statements about excluded APIs, which slightly reduce clarity.

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?

The description covers the complete lifecycle: when to call it, what it returns (status, err_msg, poll_count, elapsed_ms, result preview), and what follow-up tools to use. Without an output schema, the RETURNS section provides the needed expectation of response shape. It also accounts for the complex async run scenario and long-running workers.

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 100% and each parameter already has a detailed description with defaults, ranges, and source guidance. The tool description does not add meaningful parameter-level semantics beyond vaguely referencing 'result preview' and 'timeout elapses', so the baseline of 3 is appropriate.

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 opens with a specific verb ('Poll') and resource ('CoreClaw worker run'), and clearly states the outcome: wait until a terminal state or timeout, then return final status and optionally a result preview. It also distinguishes itself from get_worker_run by explicitly noting it avoids manual polling loops.

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 description includes dedicated WHEN TO USE and WHEN NOT TO USE sections, naming concrete alternatives like get_worker_run, verify_run, list_worker_run_results, and get_worker_run_log. It also gives workflow context (call after run_worker or rerun_worker_run) and mentions slow worker durations (60-285s) to justify polling.

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