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

Adds real cost and lifecycle context the annotations cannot express: 1 transcript credit per successful request even for an empty list, and the pending/processing → poll get_video_list with jobId recovery path. Annotations declare destructiveHint=true and idempotentHint=false; the credit-charging disclosure explains the cost side effect, though the description never addresses repeated calls / non-idempotency directly, which is the remaining gap.

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 purpose, then mode choice, then cost and error handling; every sentence carries operational information. It is on the long side (six sentences) but nothing is redundant filler.

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?

For a credit-charging, open-world listing tool with no output schema, it covers mode tradeoffs, scope exclusions, cost, and the async polling path. It does not describe what metadata fields come back or how many results flat mode returns per item, which is the only material omission.

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 67% and maxVideos has no schema description, so the description compensates by tying it to a use case ('a small maxVideos to see its latest Videos-tab uploads'). It reinforces mode semantics (full is slower, missing dates remain null) and the url requirement for full-mode single-video lookups beyond what the schema states.

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 ('List video metadata from one YouTube channel or playlist') plus the single-video variant via mode full. It clarifies the boundary against transcription ('Does not transcribe') and names the sibling used for async polling, so an agent can place it among get_transcript/get_video_list without inspecting schemas.

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?

Explicit selection rules: default flat for normal listings, full only for exact upload dates, use a known video URL for a specific-video question, and find the URL in a flat channel listing first if only a title is known. It also gives a concrete usage pattern (channel URL + small maxVideos for latest Videos-tab uploads) and states the Shorts/live tabs exclusion.

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