attach_debug

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

Discloses significant limitation: netcoredbg does not support justMyCode in attach mode, leading to unreliable debugging and incomplete stack traces. Notes this is an upstream limitation. Annotations only include openWorldHint:false, so description adds valuable behavioral context beyond annotations.

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?

Efficiently structured with strong front-loaded warning, then limitation, then usage conditions, then parameter. Every sentence adds value; no wasted words.

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?

Covers the tool's purpose, limitations, and parameter completely for a single-param tool with no output schema. Could mention that after attaching, other debug tools become usable, but the context of sibling tools makes this implicit.

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?

For the only parameter process_id, description explains it is a PID of an already-running .NET process and emphasizes NOT for normal debugging. This adds meaning beyond the schema (which only defines it as integer).

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?

Description clearly states the tool attaches to an already-running .NET process for debugging, distinguishing it from start_debug. Verb 'attach' and resource 'debug process' are specific.

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?

Explicitly advises against using this tool ('AVOID - Use start_debug instead'), details when it might be necessary (must debug an already-running process that cannot be restarted), and warns against using it when start_debug fails. Also references escape hatch for further options.

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