Debugger: Step

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

Annotations already mark it as non-readonly and non-idempotent, and the description is consistent with that. It adds genuine context beyond the annotations: the HALTED precondition and the asynchronous protocol implied by 'Follow with debugger_wait_for_stop to get the new location', which tells the agent the step result is not returned directly. No contradiction with annotations.

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?

Three sentences with zero filler and the core action front-loaded in the first clause. The kind enumeration earns its place by adding semantics rather than repeating the schema, and the HALTED plus wait_for_stop guidance is packed into two short sentences.

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 no-output-schema mutation tool, it covers the essential invocation context: the precondition, the parameter semantics, and where to obtain the new location (debugger_wait_for_stop). The remaining gaps are minor but real — the immediate return value of the step call itself and the failure behavior when the target is not halted are unspecified.

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%, so the baseline is 3, but the description adds meaning beyond the bare enum: 'over' means next line skipping calls, 'in' enters the call, 'out' finishes the current function. It also confirms the default for kind. Device and threadIndex are already well documented in the schema, so no compensation needed there.

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?

States a specific verb and resource — 'Single-step the halted thread' — and enumerates the three step kinds (over/in/out) with their meanings. The verb 'single-step' and the HALTED precondition inherently distinguish it from debugger_continue and debugger_pause, but it never names an alternative explicitly, so sibling differentiation is implicit rather than explicit.

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?

Gives a clear when-to-use condition ('Requires the target to be HALTED') and workflow sequencing ('Follow with debugger_wait_for_stop to get the new location'). It does not, however, state when not to use it or name the alternative (debugger_continue) for free-running resume, which keeps it just short of fully explicit.

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