debugger_step

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

Without annotations, the description carries full burden of behavioral disclosure. It reveals that stepInto/stepOver/stepReturn/stepContinue operate in batch mode (step + getStack), which is additional context beyond the schema. No contradictory behaviors are mentioned.

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?

Two concise sentences. The first defines the tool's purpose, and the second efficiently explains the two behavioral modes. No unnecessary words.

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 (3 parameters, 1 required) and lack of output schema, the description covers the essential behavioral modes and parameter relationships. It omits details about prerequisites (e.g., active debugger session) and error conditions, but is adequate for the stepping context.

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 100%, but the description adds value by clarifying the batch vs action mode distinction for step_type and indicating that uri is required only for certain step types. This helps agents understand parameter dependencies beyond the schema.

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?

Description clearly states 'Execute a debug step' and lists all step types, differentiating batch mode (stepInto/stepOver/stepReturn/stepContinue) from action mode (stepRunToLine/stepJumpToLine/terminateDebuggee). This effectively distinguishes it from sibling tools like set_debugger_breakpoint or debugger_goto_stack.

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 explains the two modes of operation (batch vs action) and implies when to use each based on step type. However, it does not explicitly state when not to use this tool or provide alternatives for related actions like breakpoint insertion or stack navigation.

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