trace_start

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

No annotations are provided, so the description fully covers behavioral aspects. It details that each method gets a server-side trace breakpoint, auto-continues, request flows at near-normal speed, debug state unaffected, and that includeExceptions captures unhandled exceptions. 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?

The description is concise at about 4 sentences, front-loaded with the main purpose. Each sentence adds value. Could be slightly more streamlined, but overall efficient and well-structured.

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 no output schema, the description sets expectations for what the tool does and how it interacts with sibling tools. It mentions the one-trace-at-a-time limitation. A minor gap is the lack of explanation about behavior if a new trace is started while one is active.

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%, so baseline is 3. The description adds minimal extra context beyond the schema, e.g., explaining that methods follow the same format as breakpoint_set_function. It does not significantly enhance understanding of parameters like captureStack or maxFramesPerEvent.

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: 'Begin tracing a set of methods.' It explains the behavior (captures call with stack and locals, auto-continues) and distinguishes it from sibling tools like breakpoint_set_function by noting it does not pause and leaves debug state unaffected.

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 implicitly conveys when to use this tool (when you want to capture calls without pausing) and explicitly mentions related tools: 'Use trace_get to read the captured events and trace_stop to remove the trace.' It also notes the constraint 'One trace active at a time.' However, it does not explicitly state when NOT to use it.

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