jdwp-mcp

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

No annotations provided, so description carries full disclosure burden. States execution pauses ('break') but omits critical debugger behaviors: performance cost of field monitoring, whether watchpoint persists across class reloads, if it triggers on identical value re-assignment, or thread-safety considerations.

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?

Single sentence of six words contains no filler. Front-loads the technical concept (Watchpoint). However, extreme brevity comes at cost of missing behavioral and contextual guidance that would be valuable for a debugging tool.

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?

Tool modifies debugger state (creating a persistent watchpoint) yet lacks output schema and annotations. Given the operational complexity of JVM/data breakpoints and rich sibling ecosystem, description insufficiently explains side effects or success/failure indicators.

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 has 100% description coverage with clear examples (class_pattern) and intent (field name). Description adds no parameter-specific syntax or semantics beyond schema, but baseline 3 is appropriate given complete schema documentation.

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 specific action (break/pause execution) and trigger condition (field modified). Uses technical term 'Watchpoint' which distinguishes it from sibling 'set_breakpoint' (line breakpoints vs data breakpoints). Could be elevated to 5 by explicitly contrasting with breakpoint siblings.

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?

No explicit guidance on when to prefer this over debug.set_breakpoint or debug.trace. Does not mention that watchpoints monitor data changes across all execution points while breakpoints target specific lines. Agent must infer usage from the label alone.

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