Terminate Debug Session

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

The description goes well beyond the idempotentHint annotation by explaining what gets freed, that the call is safe when no session exists, and that breakpoints are session-scoped rather than run-scoped. No annotation contradiction exists.

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?

Three short, high-information sentences with the core action first, then idempotence, then a meaningful behavioral caveat. Every sentence earns its place.

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?

For a simple two-parameter idempotent cleanup tool, the description fully explains purpose, side effects, safe-call behavior, and breakpoint persistence. No output schema is required to make the invocation decision clear.

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%, including a detailed projectId description and response_format enum. The tool description adds no parameter-level semantics, so the 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 states a clear verb and resource: 'Terminate the debug session' and further specifies 'free its worker and lazy-value registry.' This clearly distinguishes it from sibling trace tools like start_trace, step_trace, and resume_trace.

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?

It provides useful context for when to call it by noting idempotence ('succeeds even when no session is active') and that breakpoints survive termination. It doesn't explicitly name alternative debug-control tools or state 'use when you are done debugging,' but the guidance is nonetheless clear and practical.

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