launch_debugger

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

The description discloses the key blocking behavior ('wait until execution pauses'), which is valuable. However, given minimal annotations (no readOnlyHint), the description carries the full burden and doesn't mention other behavioral aspects like session lifecycle or error handling. It adds some context but is not comprehensive.

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?

A single, front-loaded sentence that states the action, target, and result with no superfluous words. It's concise while conveying the essential semantics.

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 is adequate for a complex tool because the schema fully documents parameters and an output schema exists. It clearly communicates the core purpose and the pause behavior. It could have elaborated on what happens after the pause, but the sibling tools and schema cover that context.

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% with all seven parameters described (cwd, args, console, script_path, just_my_code, stop_on_entry, python_executable). The description adds no parameter-specific information beyond 'a Python script,' so the baseline score of 3 applies.

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 action (Launch), the resource (a Python script under debugpy), and the outcome (wait until execution pauses). This distinguishes it from sibling tools like set_breakpoint and step_over, which operate on an already-launched session.

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 positions this as the entry point for initiating a debug session, with clear context. It doesn't explicitly name alternatives or exclusions, but the sibling list and the tool's name make when-to-use unambiguous. I didn't deduct further because no alternatives exist for launching.

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