diagnose_latency_spike

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

The description uses tags [READ][RCA] to indicate it is read-only and for root cause analysis. It explains it correlates queue depth, KV-cache pressure, etc., giving insight into its analytical nature. No annotations are provided, but the description adequately covers its behavioral traits.

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 concise and front-loaded with a strong summary tag. Every sentence adds value, including the purpose, methodology, and parameter explanation. No extraneous information.

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 explains the tool's correlation and output (ranked cause list), but lacks details on the output format (e.g., structure, scoring). With no output schema, the agent might need more specifics about what is returned. Otherwise, it covers the input and use case.

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?

The description explains the single optional parameter 'target' as 'Inference target name from config; omit for the default.' This adds meaning beyond the schema, which has 0% coverage. It tells the agent where the value comes from and the effect of omission.

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: 'Rank the probable cause of a TTFT/latency spike + the knob to turn.' It specifies the resource (latency spike) and action (rank causes), and distinguishes from siblings by noting 'call this first on why is inference slow.'

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 clear context: 'call this first on why is inference slow.' It implies this is the primary diagnostic tool for latency issues. However, it does not explicitly state when not to use it or mention alternative tools like diagnose_engine_latency.

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