capture_screenshot

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

Annotations already declare the safety profile (not read-only, open-world, non-destructive), so the description's marginal contribution is the return format (inline PNG) and the renderer prerequisite, both genuinely useful. It stops short of clarifying what happens with no active session or whether the captured image is returned inline vs. written to disk.

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 short sentences, no filler, with the core action and output format front-loaded. The pause caveat and renderer prerequisite are appended compactly.

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 no-output-schema, single-optional-param read-like tool, the description covers action, output format, and one hard prerequisite. Only minor gaps remain (behavior without a live session, inline vs. saved artifact) against an otherwise thin surface.

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 single optional sessionId is fully documented in the schema, so the baseline of 3 applies. The description adds nothing about sessionId, such as what happens when it is omitted or why follow-up tools need it.

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?

States a specific verb and resource ('Capture the current live debug session as an inline PNG'), which is more precise than the name alone. The 'live debug session' framing implicitly differentiates it from the sibling capture_scene_screenshot, but it never names that sibling to make the distinction explicit.

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?

Adds two useful usage cues: it works even when the session is paused, and it requires a display renderer. However, it gives no guidance on when to choose this over capture_scene_screenshot, and no exclusions or fallback behavior when no renderer is available.

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