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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false, but the description adds key behavioral details: it inspects leading result rows ('real-data sniff'), returns specific verdicts including ERROR_RECORD to avoid false-PASS traps, and explains the JSON return structure. This goes beyond annotations by clarifying the validation logic and the meaning of verdicts.

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 clear sections (WHEN TO USE, WHEN NOT TO USE, RETURNS, WORKFLOW) and front-loads the core purpose. However, it includes some extraneous content: the '中文触发' section is overly broad and unrelated to verification, and 'Do not call excluded internal worker-version or internal-detail APIs' is vague and not tool-specific. Still, most sentences earn their place.

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 tool with no output schema, the description is impressively complete. It covers the purpose, usage timing, alternatives, return values with all verdicts and fields, and workflow integration with sibling tools. An agent can confidently decide when and how to invoke this tool, and understand what to expect in response.

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%, so both parameters (run_id and limit) already have descriptions. The tool description does not significantly add semantic meaning beyond the schema; it only indirectly references the limit via 'real-data sniff' and the run_id via workflow examples. Since the schema does most of the work, the baseline score 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 clearly states the tool's function: 'Verify a CoreClaw worker run produced real, usable data and return a structured PASS/NO_DATA/FAILED/ERROR_RECORD verdict.' It uses a specific verb (verify), names the resource (CoreClaw worker run), and specifies the outcome (verdict). It also differentiates itself from sibling tools like get_worker_run or poll_run by emphasizing that it distinguishes genuine data from error records, which is a unique acceptance-check role.

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 provides explicit 'WHEN TO USE' and 'WHEN NOT TO USE' sections. It states to use after a run reaches a terminal state and mentions using get_worker_run_log for failure diagnosis and export_worker_run_results for full data, giving alternatives. It also clearly warns against using public search or internal APIs for this private data. This is thorough and actionable guidance.

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