step_debugger

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

No annotations are provided, so the description carries the full disclosure burden. It does convey two meaningful traits — the operation is one-shot and resumes the debuggee before returning — but omits what state is required, what happens to any unacknowledged stops, the meaning of the 10s/30s timeoutMs bound for a call that is allegedly non-blocking, and what the compact vs debug response modes return.

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?

It is only two sentences with no filler and the non-blocking behavior is front-loaded, so it is economical. However, terseness comes at the cost of clarity — 'Acknowledge one-shot line stepping and resume' is grammatically ambiguous about what is being acknowledged and what is resuming.

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 debugger-control mutation with six undocumented parameters, no annotations, and no output schema, two sentences are far short of what an agent needs. The unexplained timeoutMs also sits uneasily with the instruction to wait for stops separately, leaving the call's blocking semantics unresolved.

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% across six parameters, and the description compensates for almost none of it. The `kind` enum (into/over/out) is never explained, nor are stopId, threadId, debugSessionId, responseMode, or the timeoutMs default and cap; 'line stepping' only faintly hints at `kind` without defining its values.

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 name 'step_debugger' plus 'line stepping and resume' identifies the debugger control domain, but the verb 'Acknowledge' is ambiguous — it is unclear whether this tool performs the step, confirms a pending step, or resumes execution. It never states the key distinction among step kinds (into/over/out) that the `kind` enum implies, and it does not clearly separate itself from the sibling 'resume_debugger'.

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?

'Wait for a subsequent stop event separately' gives an implicit workflow rule: do not block here for the next stop, poll elsewhere. That is real usage guidance, but it never names the alternative (e.g. wait_for_debugger_event) or states the precondition that a session must already be stopped at a stopId.

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