debugger_get_capture

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

With no annotations provided, the description carries the full burden and it discloses the two most important behavioral traits: the payload is a snapshot captured at the last breakpoint, not live state, and the tool ships a staleness signal distinguishing a current pause from a resumed one. That directly prevents the classic misuse of treating stale data as live. It does not cover error behavior when no breakpoint has ever been hit, nor the prerequisite of an attached devtools/debugger connection, which the sibling set implies.

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?

Exactly two sentences (~50 words) with zero waste. The first sentence front-loads the composite payload and scopes it to the last breakpoint hit before introducing the alternative framing; the second sentence supplies the staleness disclosure. Every phrase earns its place and nothing repeats what the empty schema already says.

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 zero-param aggregator with no output schema, the description sketches the return content at enought granularity — top-frame scope, console, network, plus a staleness flag — for an agent to decide whether to invoke it and how to interpret the result. The gaps are the no-breakpoint-hit edge case and the requirement of a live debugging connection, both moderately relevant given the sibling tools. Neither is fatal for an agent choosing this tool.

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?

The tool has 0 parameters with trivial 100% schema coverage, so the baseline is 4. The description reinforces that no input is needed ('captured automatically', 'in one call') and there are no enums or required fields to document. There is nothing more the description could meaningfully add about parameters.

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 states a specific verb+resource: it retrieves everything captured automatically at the last breakpoint hit — top-frame scope, recent console output, and recent network requests — in one call. The 'instead of four' clause explicitly differentiates it from the individual console_get_logs / network_get_requests / debugger_get_scope family, and the em-dash list makes the exact resource unmistakable.

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?

'In one call instead of four' is an implicit but clear efficiency directive: use this tool when you want the aggregated capture in a single call rather than four separate retrievers. The staleness sentence ('Tells you whether the pause is still current or has already resumed') also states the specific situation where this tool adds value over a plain snapshot. However, it never names the alternative tools explicitly or says when NOT to use it (e.g., when only one data type is needed), so it stops short of a 5.

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