diagnose_issue

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

No annotations are provided, so the description carries the burden. It describes the analysis flow and that it returns a diagnostic report with codeHints, but does not explicitly state side effects (e.g., read-only, permissions, rate limits). Given the tool name implies diagnostics, it's likely read-only, but the description doesn't state this. It adds value with the pipeline detail and output, but safety aspects are unaddressed.

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, dense sentence with a clear pipeline using arrows and parentheses. It's front-loaded with the primary use case. Every phrase adds information, though it's a bit long. No fluff, but could be slightly more concise by trimming redundant details. Structure is logical.

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?

Given the tool's complexity and no output schema, the description explains the return values (diagnostic report with evidence chain and codeHints). It covers the workflow and cross-project behavior. However, it doesn't specify the exact structure of the report or how 'codeHints' are used, but that's acceptable given no output schema. Siblings exist for more granular actions, but this tool seems self-contained. It's fairly complete for a complex tool.

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 67%, and the description adds meaning by explaining the behavior when 'project' is omitted (cross-datasource scan). It also mentions defaults for 'range' and 'baselineOffset' in the schema, but the description reinforces these. The 'symptom' parameter's purpose is explained. For the undocumented 'start'/'end', no extra info, but the description's time-range context helps infer usage. Overall, it adds valuable parameter context, especially for 'project'.

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 purpose: a comprehensive root-cause analysis tool for diagnosing issues. It lists the analysis pipeline (trend detection, anomaly localization, dual-path probing, scoring) and distinguishes it from siblings by being the 'first choice for troubleshooting' (排障首选). It's specific about the verb (diagnose) and resource (issues).

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 usage context: it's the preferred tool for troubleshooting, and it specifies that omitting 'project' triggers a cross-datasource scan. However, it doesn't explicitly mention when to use alternatives like query_logs or compare_baseline, though the pipeline implicitly suggests it's a higher-level tool. This is clear but lacks explicit exclusions.

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