jdwp-mcp

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only implies the read-only nature via the verb 'read' but fails to describe error behavior (variable not found), return format, or the fact that it operates within a specific thread/frame context (implied by parameters but not explained).

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 brief at five words with no extraneous content, but this brevity crosses into under-specification. The single clause is front-loaded but lacks supporting context that would help an agent understand the debugging context.

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 debugging tool with multiple context parameters (thread, frame) and no output schema, the description is insufficient. It does not explain the threading model, default frame behavior (frame_index: 0), error conditions, or how this interacts with debugger state.

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 only 33% (only thread_id described). The description confirms that the 'name' parameter refers to the variable name, adding semantic clarity. However, it provides no guidance on 'frame_index' (likely stack frame depth) or the relationship between parameters (e.g., that thread_id and frame_index establish the execution context).

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 action (read) and target (local variable), distinguishing it from sibling mutation tools like debug.set_value. However, it does not differentiate from debug.inspect or debug.eval which may also retrieve variable values, nor does it clarify the scope of 'local'.

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 (e.g., debug.eval for expressions vs. debug.get_variable for simple reads), no prerequisites (e.g., requires paused thread), and no workflow context within a debugging session.

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