oc_performance_insights

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

Annotations provide readOnlyHint=false etc. The description adds behavioral context: it starts tracing (nontrivial operation), session-scoped handles are evicted on session close, and it can be disabled via environment variable. No contradictions.

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?

Two sentences: first directly states purpose and outputs, second adds essential lifecycle context. Every sentence is necessary, no redundancy.

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 6 parameters (1 required) and no output schema, the description covers key aspects: purpose, returned insights, trace_id for analysis, session scoping, and disable option. Adequate for an agent to use the tool safely.

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 the schema already documents each parameter. The description adds no new parameter-level meaning beyond listing output insights. Baseline 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 uses specific verbs ('capture', 'return') and clearly names the resource ('CDP performance trace', named insights list). It distinguishes from sibling 'oc_performance_analyze' by stating the trace_id is usable by that tool.

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 explains when to use (performance tracing) and provides lifecycle details (session-scoped, eviction on close, disable env var). However, it does not explicitly contrast when not to use this tool versus alternatives like performance_metrics or network_capture.

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