debuggerStep

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

Annotations provide readOnlyHint=false and destructiveHint=false, so the description carries burden for behavioral traits. It discloses that each step returns the new position, that stack and variables become stale, and that termination ends the debugged program. This is valuable beyond annotations and explains the side effects. No contradiction with annotations; termination is a runtime operation, not a persistent data modification.

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 sentences, front-loaded with the core purpose. The second sentence efficiently explains the return behavior and termination. No redundant fluff; every phrase contributes.

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?

The description covers the essential operational context: it must be used on a stopped process, it can terminate, and it invalidates stack/variable reads. It does not detail error cases or preconditions like 'must be attached', but these are implied by the name and the debugger toolset. With no output schema, the description reasonably summarizes what the agent needs to know for correct invocation.

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% but the schema descriptions are minimal ('type of step', 'URL for certain step types'). The tool description adds meaning by listing the possible step types (into, over, out, to a line, terminate) and clarifying that url is used for stepRunToLine/stepJumpToLine. This enriches the agent's understanding 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?

The description states a specific verb ('step') and resource ('stopped process'), and enumerates the action subtypes (into, over, out, to a line, terminate). This clearly distinguishes it from sibling debugger tools like debuggerStackTrace (reads stack) or debuggerVariables (reads variables). The purpose is unambiguous and specific.

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 gives context on when to use it: when the process is stopped and you need to advance execution. It also notes that after stepping, you must re-read stack and variables, implying a workflow. It does not explicitly name alternatives or state when not to use it, but the context among many debugger siblings makes it clear this is the stepping tool. Slight gap: no explicit 'use this instead of X'.

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