LLDB_FINISH

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

With no annotations provided, the description must carry the full burden of behavioral disclosure. It only states the basic action, omitting details such as whether it stops at the return location, returns the function's result, or what happens if the current frame is the topmost (no caller).

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 extremely concise (5 words) and avoids unnecessary fluff. However, it lacks any structural elements like a summary or bullet points, which might improve scannability. Still, it is efficient for its purpose.

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?

Given the simplicity of the tool (1 param, no output schema), the description is minimal. It fails to clarify what happens after execution (e.g., does the debugger stop? does it print the return value?). These gaps reduce completeness, especially since no output schema exists to compensate.

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 for the single parameter 'sessionId' is 100%, so the schema already describes its purpose. The description adds no additional meaning or constraints, meeting the baseline of 3.

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 'Execute until the current function returns' clearly specifies the verb (execute) and the resource (current function returns), distinguishing it from sibling tools like LLDB_STEP and LLDB_NEXT which step by instruction or line, and LLDB_CONTINUE which continues until next breakpoint.

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 provides no guidance on when to use this tool versus alternatives such as LLDB_STEP or LLDB_CONTINUE. It does not mention that it is analogous to GDB's 'finish' command, nor does it suggest typical debugging scenarios or prerequisites like having a stopped function frame.

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