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

Annotations already declare readOnly, idempotent and openWorld, so safety is covered. The description goes beyond them by disclosing cost (1 credit), the error behavior for videos without a graph (free), and the return shape. It does not document rate limits or auth, but adds meaningful behavioral context.

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 deliverable, then progressively adds the retention framing, the failure mode, and cost. Every sentence earns its place with no redundancy; nothing can be cut without losing signal.

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?

With no output schema, the description takes responsibility for explaining return values (moment, peaks, 20-part graph with links) and covers cost and the common empty-graph case. Combined with annotations that cover safety, an agent has everything needed to call this correctly.

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?

Only one parameter ('video') with 100% schema description coverage, so the schema already fully documents it (accepts ID or URL). The description adds no further parameter syntax or format guidance, making the baseline 3 appropriate.

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?

Names a specific verb and resource ('most replayed graph for a video') and enumerates its exact outputs (most replayed moment, five peaks, 20-part graph with timestamped links). This clearly separates it from siblings like get_video_details or get_transcript 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?

The description implies usage (find retention/rewatch hotspots) and adds useful operational context ('many videos have no graph; that error is free', '1 credit'), but never states when to prefer this over sibling tools such as get_video_info or get_video_details, nor any prerequisites. Usage is inferable rather than explicit.

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