set_breakpoint

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

No annotations are provided, but the description reveals that breakpoints work on bundled scripts and that urlRegex is an alternative. It also notes that hits are observed via get_paused_state, indicating the tool doesn't return hit status. Could be more explicit about side effects, but sufficient for no 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?

Two sentences that are direct and informative. Every word adds value; no redundancy or filler.

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 tool has 7 parameters and no output schema. The description covers the key parameters (url, urlRegex, pageId) and refers to a sibling for result observation. It could mention the return value (likely ack) or confirmation, but overall it's fairly complete for the complexity.

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 baseline is 3. The description adds value by explaining the use of urlRegex for bundled scripts and default pageId, and contrasting url vs urlRegex. This provides semantic context beyond parameter names and descriptions.

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 explicitly states the tool sets a breakpoint by URL or URL regex, in the main process or a renderer page. It clearly distinguishes from sibling tools like remove_breakpoint, list_breakpoints, and get_paused_state.

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?

Provides explicit guidance: use urlRegex for bundled scripts, and refer to get_paused_state to observe hits. It also implies when to use this tool versus others (e.g., pause/resume for immediate suspend).

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