Diagnose Performance

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

Annotations already state readOnlyHint, idempotentHint, and destructiveHint false. The description adds behavioral context by noting the multi-step nature of the diagnosis and the specific data sources it inspects (e.g., slow SQL, service hotspots). It also explains the report structure (severity levels and suggested actions). This exceeds the baseline but doesn't disclose potential runtime or cost implications, keeping it at 4.

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 two sentences, front-loaded with the main action, then details and output. Every word earns its place — no redundancy or filler. It is succinct yet informative.

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 provides a solid overview of inputs, actions, and outputs, but with no output schema, it does not detail the report structure beyond severity and suggested actions. It omits any clarification of what obj_type filters (e.g., specific object types) and any indication of the operation's cost. Given the tool's complexity, the description is reasonably complete but leaves some contextual gaps, justifying a 4.

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 100%: both parameters (obj_type and time_range_minutes) have descriptions. The tool description does not add parameter behavior beyond what the schema provides, so it relies on the schema baseline. The description neither enhances nor detracts from the parameter understanding, meriting a 3.

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 with a specific verb and resource: "Perform automated multi-step performance diagnosis." It enumerates the checks (system counters, active services, error patterns, slow SQL, service hotspots) and the output (structured diagnostic report with severity ratings and suggested actions), distinguishing it from sibling tools that focus on individual metrics.

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 implies when to use it — for a comprehensive, multi-step diagnosis rather than a single metric — but it does not explicitly name alternatives or exclusions. The context is clear: it is a holistic diagnostic report tool, unlike the granular get_* sibling tools. However, there is no explicit 'when not to use' guidance, so it falls short of a 5.

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