rad_attach

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

Annotations only declare the non-read-only, non-destructive, closed-world profile; the description adds genuinely new behavioral facts — the call blocks waiting for a debug stop and may pause the target. That pause warning is exactly the kind of side effect an agent needs before calling. It stops short of explaining how timeout or failed attach behaves.

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 short sentences, action first, hazard second. Nothing is wasted and the key caveat is front-loaded.

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?

An output schema exists, so return values need not be described. But for a blocking debugger attach with a required session handle and an undocumented timeout, the definition is thin — it omits the session prerequisite and what happens on timeout or failed attach.

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 0%, so the description must carry parameter meaning, but it only glosses 'pid' via 'existing local application PID'. session_id (a required string) and timeout (default 15, units unspecified) are never explained anywhere.

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 specific verb and resource ('Attach to an existing local application PID'), which implicitly distinguishes it from rad_launch. It doesn't name a sibling explicitly, but the 'existing' qualifier makes the attach-vs-launch split inferable.

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?

Usage is only implied: attaching to an already-running process. There is no explicit statement of when to prefer this over rad_launch, nor any mention of prerequisites such as needing a session from rad_create_session first, despite session_id being required.

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