YouTube

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

Beyond the read-only, open-world, idempotent annotations, the description discloses important behavior: per-resource credit costs, free failures, cache acceptance via max_age_days, cursor pagination, and that include_extras is slower and more error-prone. It also explains the nonlinear transcript pricing model, which is critical for an agent deciding whether to call that resource.

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 long, but the length is justified by 18 resources. It is front-loaded with invocation rules and cost/cursor behavior, then uses a compact resource list with only essential per-resource details. There is little wasted wording.

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 the tool's complexity, 13 top-level parameters, nested `params`, and no output schema, the description provides enough invocation and behavioral context to call the tool correctly. It covers resource selection, required arguments, paging, caching, credits, and special pricing cases, leaving only minor output-shape details unspecified.

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?

Although schema coverage is already 100%, the description adds substantial meaning by mapping each resource to its required inputs, noting which resources are paged, identifying optional parameters such as include_extras, and directing extra resource-specific parameters into `params`. This goes well beyond the schema's generic parameter descriptions.

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 identifies the tool as YouTube data and enumerates every supported resource, from channels and videos to transcripts and comments. This is specific enough for an agent to understand the tool's domain and capabilities, and to distinguish it from non-YouTube siblings such as tiktok or instagram.

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 explains exactly how to invoke the tool: choose a `resource`, pass its parameters at top level, put extras in `params`, and use `max_age_days` for free cached results. It also lists required arguments and paging behavior per resource. However, it does not explain when to choose this tool versus overlapping siblings such as get_transcript, search, get_profile, or get_comments.

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