get_frames

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. Description adds that it returns optimized, deduplicated JPEG frames, which is beyond annotation. No contradictions.

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?

Description is 6 lines, well-structured with bullet points for modes and supported URLs. Every sentence adds value with no repetition. Front-loaded with key action.

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?

Given no output schema, description clarifies return format (JPEG frames). Annotations cover safety. Sibling tools exist but this tool's description differentiates it well. Could mention that it is non-destructive but annotations already indicate that.

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 describes url and options with defaults and ranges. Description adds meaning by explaining the purpose of 'dense' mode and scene-change detection, which is not fully captured in schema. Schema coverage is 50%, description compensates.

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?

Description clearly states it extracts key frames from a video URL without transcript or metadata. It distinguishes from siblings by specifying two extraction modes and supported URL types. The verb 'Extract' and resource 'key frames' are specific.

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?

Description gives clear guidance on when to use scene-change detection vs dense sampling, and lists supported URL types. Does not explicitly exclude other scenarios but provides enough context for correct usage.

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