lldb_run

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

Annotations provide readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false. The description adds valuable behavioral context beyond annotations: it details the multi-step process (loads executable, sets breakpoints, runs program, returns state), specifies what happens when stopped, and describes the return content. No contradiction with 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?

The description is well-structured with a clear opening sentence, numbered steps, and separate Args/Returns sections. It's appropriately sized but could be slightly more concise by integrating the steps into the main flow. Every sentence adds value, though the formatting is slightly verbose.

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 tool's complexity (debugging execution), rich annotations, and presence of an output schema (which handles return values), the description is mostly complete. It covers the purpose, process, and key parameters, though it could benefit from more usage guidelines and parameter details to fully compensate for the 0% schema coverage.

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%, but the description adds minimal parameter semantics: it mentions 'optional breakpoints' and 'optionally stopping at entry', and references 'RunProgramInput with executable, args, and breakpoints'. However, it doesn't fully compensate for the low coverage by explaining all parameters like environment or working_dir. Baseline 3 is appropriate as it adds some meaning but not comprehensive details.

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 clearly states the specific action ('Run a program under the debugger') and resource ('executable'), distinguishing it from siblings like lldb_set_breakpoint (which only sets breakpoints) and lldb_run_command (which runs debugger commands). The four-step breakdown provides explicit scope.

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 for running programs with debugging, but lacks explicit guidance on when to use this vs alternatives like lldb_run_command or prerequisites. It mentions 'optional breakpoints' and 'optionally stopping at entry', which gives some context but no clear exclusions or comparisons to siblings.

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