lldb_watchpoint

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

Annotations indicate this is a non-readOnly, non-destructive operation, but the description adds valuable behavioral context: it explains what triggers the break (variable access), defines three specific watch types with their behaviors, and mentions the confirmation return. This goes beyond annotations by detailing the tool's specific debugging behavior and output.

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 efficiently structured with a clear purpose statement, bullet-pointed watch type definitions, and labeled Args/Returns sections. Every sentence adds value with no redundancy. The information is front-loaded with the core functionality stated first.

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 moderate complexity (debugging operation with multiple watch types), good annotations, and the presence of an output schema (which handles return value documentation), the description is reasonably complete. It covers the core behavior, watch type semantics, and basic parameter context, though additional parameter details would improve completeness further.

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?

With 0% schema description coverage (the schema has descriptions but they're not counted in coverage), the description provides some parameter context by mentioning 'variable and access type' and listing watch types, but doesn't explain the executable parameter, condition parameter, or the nested WatchpointInput structure. It adds partial meaning but doesn't fully compensate for the schema coverage gap.

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 ('Set a watchpoint to break') and resource ('when a variable is accessed'), distinguishing it from sibling tools like lldb_set_breakpoint (which likely sets breakpoints at code locations) or lldb_examine_variables (which likely inspects variable values). The description explicitly defines what a watchpoint does in this debugging 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 context (debugging with LLDB when needing to monitor variable access) but doesn't explicitly state when to use this tool versus alternatives like lldb_set_breakpoint or lldb_examine_variables. It provides watch type definitions that help understand different use cases, but lacks explicit guidance on tool selection.

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