debug_attach

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

No annotations are present, so the description carries the full burden of behavioral disclosure. It discloses that the tool returns a session_id and that it attaches to a running target, but it does not mention side effects (e.g., pausing the target), error behavior, or the effect of calling with no parameters.

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?

Two sentences front-load the core action and return value, then add targeting guidance. No filler words; every clause 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 tool with four optional parameters and no output schema, the description explains the return value and two common attach modes. But it omits the adapter parameter, leaves the no-parameters case ambiguous, and contains the unsupported program-name reference, so an agent still lacks full 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%, so the baseline is 3. The description adds a useful mapping (Python→host/port, Rust→pid), but it also references a 'program name' for Rust that is not present in the input schema, which is misleading and partially invalidates the added guidance.

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?

States a concrete action ('Attach to a running debug server or process') and the resource. The verb 'attach' clearly distinguishes it from sibling tools like debug_launch and debug_disconnect. The return-value note reinforces purpose.

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?

Gives language-specific usage context ('For Python: provide host/port. For Rust: provide pid or program name.'), which helps an agent choose parameter modes. However, it never explicitly contrasts with debug_launch or says when not to use it; the 'running' qualifier only implies the tool is for existing targets.

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