continue_or_step

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

No annotations are provided, so the description bears the full burden of behavioral disclosure. It does disclose the precondition that the target must be stopped, which is useful context. But it fails to disclose that each action mutates the target's execution state, what happens when the target is actually running or the requested action is invalid (e.g., StepOut with no call frame), or whether these operations are side-effecting and irreversible.

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?

A single sentence with zero wasted words: all four actions are front-loaded, and the precondition is appended economically. The listing of four actions is somewhat flat rather than prioritized, but for the content it contains, the structure is appropriately sized and scannable.

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?

With no annotations and no output schema, the description must stand alone, and it leaves significant gaps: where targetId comes from, how to choose among Continue/Step/StepIn/StepOut, error behavior when the target is not stopped, and what the caller observes as a result. The essential action set and precondition are present, but an agent has too little to confidently invoke the tool correctly or recover from invalid use.

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 0%, so the description must compensate for the schema's silence — and it doesn't. The description merely echoes the enum action names without explaining what each actually does or when to choose one over another, and it never clarifies what targetId refers to (presumably a target from list_debug_targets or a breakpoint hit). An agent must infer both parameters' practical meaning.

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 names four specific debugger-control verbs (Continue, step over, step in, step out) and a clear resource (a stopped target), so an agent can tell this is the execution-resumption/stepping tool. It implicitly distinguishes itself from siblings like suspend_target (the inverse operation) and connect_debugger/attach_targets (connection setup). It falls short of a 5 only because it never explicitly contrasts itself with any sibling.

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 phrase 'in a stopped target' implies the key precondition — use this only when the target is suspended — which is meaningful usage guidance. However, the description gives no explicit when-not-to-use conditions, no alternative tool mentions (e.g., suspend_target for pausing, poll_debug_events to check state), and no guidance on choosing between the four actions.

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