obs-get-source-screenshot

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

With no annotations supplied, the description carries the full disclosure burden, and it does contribute one important behavioral fact: the return value is native MCP ImageContent, not a path or base64 string. It says nothing about permissions, latency, whether the call fails when the source is hidden or the scene isn't rendering, or whether the capture is a live frame vs. a cached frame.

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?

A single front-loaded sentence with no filler; the key differentiator (ImageContent for vision models) arrives before any detail. Minor deduction because there is no structural separation between what it does and when to prefer it.

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 6-parameter tool with no annotations and no output schema, the description usefully compensates for the missing output schema by naming the return type. It still leaves the agent without error conditions, source-resolution behavior when both sourceName and sourceUuid are given, or any note on cost/latency of repeated captures.

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 description coverage is 100%, with defaults and scaling rationale already documented for imageWidth, imageFormat, and imageCompressionQuality. The description adds only the 'source or current scene' framing, which the sourceName schema entry already states, so it does not go beyond structured data. Baseline 3 applies.

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 gives a specific verb+resource ('Gets a screenshot of a source or current scene') and states the output medium ('native MCP multimodal ImageContent'). That medium clause implicitly separates it from the sibling obs-save-source-screenshot, but the sibling is never named, so an agent must still infer the distinction.

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?

'for vision models' hints at the use case (returning pixels for a model to inspect rather than persisting a file), which is implied guidance. There is no explicit when-not, no mention of obs-save-source-screenshot as the alternative for saving to disk, and no stated prerequisites such as the source being present in the current scene.

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