youtube_get_frame

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

The description adds meaningful behavioral context beyond the annotations (readOnly, idempotent, destructive=false). It discloses that the returned JPEG is ephemeral, that extraction is best-effort, and that the timestamp is approximate ('near'), which is valuable for setting expectations. It also states the return format (metadata plus MCP ImageContent). No contradiction with 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?

The description is two sentences with no filler. The core function leads, and the second sentence efficiently covers return type and accuracy limitations. It is appropriately sized for the tool's complexity and well front-loaded.

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 relatively simple read-only extractor, the description covers the essential return value (metadata plus image), accuracy limits, and the schema covers all parameters. The annotations handle safety. It lacks some details like error cases or authentication, but these are not critical given the readOnly/idempotent hints and the tool's narrow scope.

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 schema already covers all parameters (100% coverage), so the baseline is 3. However, the description's phrase 'near an integer-millisecond timestamp' adds precision semantics to timestamp_ms, clarifying that the given value is a target rather than an exact millisecond. This goes beyond the schema's simple 'Frame timestamp in integer milliseconds.'

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 clearly states a specific action: 'Extract one ephemeral JPEG near an integer-millisecond timestamp.' This uses a strong verb ('extract') and a concrete resource (a JPEG frame), and it is distinct from sibling tools that search or retrieve metadata/transcripts. It immediately communicates the tool's purpose.

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?

The description implies usage context (when a video frame is needed) but provides no explicit guidance on when to choose this tool over siblings or any exclusions. Unlike the calibration example, it does not name alternative tools or describe scenarios where this tool is not appropriate. The 'near a timestamp' phrasing does hint at precision trade-offs but not usage boundaries.

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