youtube_analytics_retention

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

With no annotations provided, the description carries the behavioral disclosure burden. It discloses the output shape (100 data points, relative retention comparison) which is useful. However, it doesn't disclose things like whether data may be sparse/empty without enough views, the granularity of the 100 points (are they time-bucketed?), or any auth/attribution requirements. The description adds moderate value but has gaps.

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 concise and well-structured, front-loading the purpose in the first line, then adding the return format, then the Args section. The Args section is redundant with the schema (which already lists parameters and defaults), adding date format detail that belongs better in the schema description field, but overall it's tight and organized.

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?

No output schema exists, so the description partially compensates by describing return values (100 points, relative retention). The tool is moderate complexity—a single-video analytics query. The description covers purpose, output shape, and parameter formats. Missing: how the 100 points map to video length, whether partial data occurs for short videos, and clarity on retention vs average view duration. Adequate but not comprehensive.

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 0%, meaning the description must compensate for undocumented parameters. The description lists video_id, start_date, end_date and explains the date format (YYYY-MM-DD) plus defaults (28 days ago, today), which is helpful and exceeds the bare schema. However, it doesn't explain what video_id should look like or date range constraints. It partially compensates but with only 3 params the moderate explanation earns a 2 rather than a 1.

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 the tool gets audience retention curves for a specific video, with a specific verb+resource. It distinguishes from siblings like youtube_analytics_overview and youtube_analytics_video_detail by focusing on the retention curve specifically. It could be more explicit about distinguishing from analytics siblings, but the purpose is clear.

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 (retention analysis for a single video) but doesn't explicitly state when to use this vs alternatives like youtube_analytics_video_detail or youtube_analytics_overview. No exclusions or alternative recommendations are provided. The 100 data points and relative retention framing hints at intended use but doesn't clarify selection criteria.

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