巡检任务质量

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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It says '巡检' (inspect), implying a read-only operation, but does not explicitly state that it does not modify data, whether it requires specific job state, or if it affects running jobs. It also does not mention how many issues it returns beyond the max_issues parameter, leaving agent uncertain about side effects.

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 a single sentence with no fluff, front-loading the purpose and findings. It is appropriately sized for an MCP tool description. However, it could be slightly more structured by adding a separate 'use when' clause, but as-is it is concise and to the point.

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 tool has three parameters with no schema descriptions, no annotations, and only an output schema. The description covers the primary purpose but omits parameter semantics and behavioral caveats. While output schema exists to explain returns, the agent lacks sufficient information to invoke the tool correctly (e.g., what max_issues accepts, whether use_latest_rules matters). This is incomplete given the tool's complexity.

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 does not explain any of the three parameters. job_dir is implied by '巡检已输出页面', but max_issues and use_latest_rules are completely unexplained. The agent cannot infer what these parameters control or how to set them correctly, which is a critical 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?

The description clearly states the verb '巡检' (inspect/audit) plus the resource '已输出页面或运行中逐页缓存' (output pages or running per-page cache), and enumerates specific issues detected (low-confidence pages, missing pages, split title residue, chart noise residue). This distinguishes it from sibling tools like diagnose_pdf or run_health_check, which focus on broader health or PDF-specific diagnostics.

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 context on when to use: '已输出页面或运行中逐页缓存' indicates it works post-output or on running jobs. However, it does not explicitly mention alternatives or exclusions, such as 'use diagnose_pdf for detailed PDF issues' or 'do not use while job is still running'—though the 'running' mention hints at that. Clear context but no explicit negative guidance.

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