jdwp-mcp

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

No annotations are provided, yet the description fails to disclose execution behavior—specifically that execution resumes immediately and pauses when the current function returns. It also omits default thread selection behavior when thread_id is omitted.

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?

Extremely terse at 4 words with zero redundancy. While appropriately front-loaded, the extreme brevity approaches under-specification rather than ideal information density.

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?

For a debugger control-flow tool with numerous stepping siblings and no annotations/output schema, the description is inadequate. It should explain that execution resumes until the current call stack frame returns, and clarify thread selection defaults.

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 is 100% (thread_id fully documented with type/format), establishing baseline 3. The description adds no information about the parameter semantics, though none is required 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?

Uses specific debugger terminology 'step out' with clear target 'current frame', which is standard debugging vocabulary. However, it does not explicitly distinguish from sibling tools like step_into/step_over or explain what a 'frame' represents in this 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?

Provides no guidance on when to use this tool versus alternatives (step_into, step_over, continue) or prerequisites such as requiring the debugger to be in a paused state.

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