debug_step

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

With no annotations, the description fully discloses behavior: it can block and return a snapshot (top frame, locals, output) similar to breakpoint_wait when waitTimeoutSeconds > 0, otherwise returns immediately. No contradictions.

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 two sentences, no unnecessary words, and front-loads the core purpose. It packs significant information efficiently.

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?

Despite no output schema, the description covers the return value for the blocking mode. All parameters are explained with their conditional use. The tool's behavior is completely described for its complexity.

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% (baseline 3). The description adds value by explaining that maxLocalsPerScope and maxRecentOutputLines are only used when waitTimeoutSeconds > 0, and clarifies the effect of waitTimeoutSeconds. This goes beyond the schema descriptions.

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 tool's function: single-step the debuggee with three step kinds (in, over, out). It distinguishes itself from siblings like breakpoint_wait by noting it can return the same snapshot when waitTimeoutSeconds > 0.

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: immediate return vs. blocking wait with enriched snapshot. It implicitly guides the agent on when to use each mode, though it does not explicitly contrast with other stepping tools like debug_continue.

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