capture_runtime

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

Annotations only declare readOnlyHint=true and openWorldHint=false; the description goes well beyond by explaining that it captures the live frame buffer reflecting running scripts/physics/animation, that it works across WebGL and WebGPU backends, and that meta.deviceType reports the backend. This output-format and backend-variability context is genuinely additive.

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?

Front-loaded with the core verb+resource and emphasis on RUNNING to prevent misuse. The 'live frame buffer / reflects running' sentence slightly restates the earlier RUNNING point, but the rest is dense and useful with no padding.

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?

No output schema exists, yet the description discloses the return format (downscaled WebP) and a key returned field (meta.deviceType), plus the launch_start dependency. An agent has everything needed to call it correctly and interpret the result.

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 takes zero parameters, so the baseline is 4. There is no parameter surface for the description to explain, and it correctly offers none.

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?

Specific verb (Screenshot) plus a precisely scoped resource (the RUNNING Launch instance, explicitly not the editor preview) delivered as a downscaled WebP. It names capture_viewport as the sibling it is not, so an agent can distinguish the two without opening either schema.

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?

States the hard precondition (requires launch_start first) and gives an explicit 'When NOT to use' clause that routes the agent to capture_viewport for edit-time visuals. Both the selection context and the exclusion are spelled out.

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