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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely new behavior: newest-first ordering, bounded pagination, and the caveat that availability reflects catalog state rather than a playback guarantee. It also discloses the access model ("open the website to watch under normal access rules"), which is real added value. It omits any note on error or empty-result behavior.

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?

Four compact sentences with purpose front-loaded first and caveats after; almost no waste. The closing sentence about the website is slightly tangential to the search operation but does carry useful context.

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 an output schema present, return values need no explanation, and the description covers matching semantics, ordering, pagination shape, and freshness caveats. The remaining gap is per-parameter meaning for limit and offset on a five-parameter tool with zero schema coverage.

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%, so the description carries the burden. It does clarify query semantics (literal keyword matching against title/description/channel title) and confirms channelId and hasTranscript as filtering dimensions. However, limit and offset are only obliquely hinted at via "bounded pages", and no parameter names, ranges, or defaults are surfaced.

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 ("Find videos") plus the exact match surface ("literal keywords in video title/description or channel title"), which separates it from the channel/comedian/special searchers in the sibling set. It stops short of naming a specific sibling to use instead, so the differentiation is inferred from the resource noun rather than stated.

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?

"Metadata search does not search spoken content" is an explicit when-not statement that steers an agent toward transcript-based lookups, and "with a ready transcript" names the condition that selects the hasTranscript path. The description never names the recommended alternative tool (e.g. get_comedy_transcript), leaving the routing only implied.

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