Audience retention curve for one video

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

Beyond the readOnly and idempotent hints in annotations, the description discloses a critical behavior: the underlying API silently accepts lists but the tool rejects them to avoid mislabeling. It also explains the interpretation of relativeRetentionPerformance (0-1, 0.5 median), which is valuable context that goes beyond what annotations provide.

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, front-loading the core purpose in the first sentence and adding critical usage constraints in the second. No unnecessary words, and each sentence earns its place.

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 compensates by outlining the data granularity (1% slices) and the two metrics. It also explains the list-rejection behavior. This is sufficient for a read-only tool with comprehensive annotations and schema descriptions, though it stops short of fully describing the response structure.

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 input schema already documents all 5 parameters with descriptions, so the baseline is 3. The description adds meaning by explaining the 1% slice granularity and the semantics of relativeRetentionPerformance, which enriches understanding of the metrics parameter and the tool's output.

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 explicitly states 'The retention curve for a single video' and defines each metric (audienceWatchRatio and relativeRetentionPerformance), making the tool's purpose unambiguous and distinct from sibling analytics tools. It clearly specifies the resource (a single video) and the action (retrieving retention curve data).

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?

It provides clear usage guidance: use this tool to find drop-off points, and explicitly warns that lists are rejected, so call once per video. However, it does not name alternative sibling tools for comparison, so it falls short of full 5-level guidance.

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