trace_start

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

No annotations are provided, so the description bears full responsibility. It discloses that tracing auto-continues, runs at near-normal speed, does not affect debug state, and that includeExceptions captures unhandled exceptions. This is thorough behavioral coverage.

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 three sentences long, front-loads the core purpose, and contains no redundant information. Every sentence adds value: what the tool does, how to read/stop, and a key constraint (one active trace).

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 covers the tool's lifecycle, constraints, and key parameters. It lacks explicit mention of the return value (if any), but the tool likely returns a confirmation, which could be inferred. Overall, it is complete for a tool with 6 parameters and no output schema.

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%, meaning every parameter has a description in the schema. The tool description adds general context (e.g., the purpose of includeExceptions) but does not provide additional semantic details beyond what the schema already gives. 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 clearly states the tool begins tracing a set of methods with specific behavior (captures top stack and locals, auto-continues). It distinguishes itself from siblings like trace_get and trace_stop by mentioning them as complementary tools.

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 mentions using trace_get to read events and trace_stop to remove the trace, and notes that only one trace can be active at a time. However, it does not explicitly compare to alternatives like breakpoint_set_function or provide when-not-to-use guidance.

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