Continue

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

Annotations already indicate this is not read-only, and the description adds useful behavioral detail: it returns immediately and behaves differently based on the target state. It does not describe what happens if the target is in neither state or what the return value means, but the non-blocking behavior is a meaningful disclosure.

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 short sentences deliver the action, the return behavior, and the follow-up tool recommendation with no wasted words. The most important behavior is front-loaded.

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 simple debugger continuation tool, the description covers the start/resume distinction, immediate return, and the next step. Minor gaps like error handling and return value format are left out, but the schema and annotations already cover enough 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%, and the sessionId parameter already has a full description in the schema. The tool description adds no parameter-level meaning, so the baseline score of 3 is appropriate.

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 starts an isolate in 'awaiting_start' or resumes a paused target, so the agent knows the core action and resource. However, it does not distinguish itself from the sibling debug_resume, which likely also resumes paused targets.

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 tells the agent when to call it ('if still awaiting_start' or 'resume a paused target') and gives a direct follow-up instruction to use debug_wait_for_pause after an expected breakpoint. It does not explicitly contrast it with debug_resume or other alternatives.

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