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

Annotations already declare readOnly, openWorld, and non-destructive, so the safety profile is covered. The description adds genuinely useful non-annotation context: per-video billing, no charge on failures, per-call limits (15 feed / 100 full), and a free-account requirement. Rich, but annotations carry much of the load.

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?

Dense but front-loaded, leading with purpose and mode behavior before pricing details. Every sentence carries information, though the pricing and billing sentences add length an agent may not always need. 5,

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 proactively lists return fields for each mode, and covers mode behavior, limits, billing, auth requirements, and endpoint equivalence. Nothing needed to invoke correctly appears to be missing.

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 coverage is 100%, so the baseline is 3, but the description goes further by explaining what each mode returns (feed fields vs the full watch-page field set) and the per-mode limit ranges, adding meaning beyond the schema text.

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?

States a specific verb and resource (video metadata for YouTube channels and video URLs) and immediately scopes it against siblings with 'no transcripts,' routing agents away from get_youtube_transcript. The feed vs full mode split makes the exact retrieval behavior unambiguous.

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?

Gives explicit mode-selection conditions: 'feed' (default) for latest uploads and cheap pricing, 'full' for every watch-page field and deeper history, plus the rule that video URLs always return full rows. Combined with the 'no transcripts' exclusion, an agent can choose this tool and its mode without inference.

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