kd_attach

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

With no annotations, the description carries the burden of behavioral disclosure. It does state the default blocking behavior ('by default wait until the target connects'), which is useful. However, it doesn't disclose what happens on timeout, whether the tool returns immediately after starting kd.exe, what side effects occur (e.g., does it modify VM state?), or whether it requires the VM to be running. The description is honest but thin.

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 a single sentence that front-loads the core action and default behavior. It's efficient and doesn't waste words. It could add a bit more context, but for its length it's well-structured.

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 6 parameters and no output schema, the description is somewhat thin. It doesn't explain what happens after the target connects, what the return value looks like, or what prerequisites exist (e.g., VM must be running, kd_setup_host/guest must have been run). The sibling tools suggest a workflow (kd_setup_host, kd_setup_guest, kd_attach, kd_break, kd_go), but the description doesn't situate itself in that workflow. However, the schema covers parameters well, and the core behavior is stated.

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%, so the schema already documents all 6 parameters. The description adds minimal value beyond the schema—it doesn't explain how parameters like key, port, or symbol_path override vms.yaml settings, or how timeout interacts with wait_for_target. Baseline 3 is appropriate since the schema does the heavy lifting.

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 specific verb ('Start kd.exe') and resource ('for the VM'), and mentions the default wait behavior. It's clear enough to distinguish from siblings like kd_break or kd_go, though it doesn't explicitly name an alternative or elaborate on what 'attach' means in this context.

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 implies usage: call this to start kd.exe and wait for the target. It doesn't explicitly state when to use this vs alternatives like kd_setup_host or kd_setup_guest, nor does it mention prerequisites like the VM needing to be running. The wait_for_target parameter is described in the schema, but the description doesn't add context about when you'd want to disable it.

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