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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, and the description restates part of that ('Read-only: returns public data and changes nothing'). The genuinely additive detail is the billing behavior — 'Costs 1 credit per request' — which no annotation conveys, plus the note that transcripts come back in the same call and default to the video's own caption track.

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?

Three compact sentences, front-loaded with the purpose and the returned-field list, then behavior, then cost. The 'including Shorts and live streams' clause duplicates the url schema description, and the read-only sentence partly restates annotations, but neither bloats the overall definition.

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?

There is no output schema, so the description carries the burden of describing returns — and it does so with a concrete field list plus the transcript. Combined with the credit-cost disclosure and transcript language default, an agent can call this tool correctly without further information.

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 100%, so all three parameters (url, includeTranscript, transcriptLanguage) already carry documentation including accepted link forms and the BCP-47 fallback. The description reinforces link-form flexibility ('any video link, including Shorts and live streams') and language choice but adds no new parameter-level semantics such as error behavior for unsupported languages or invalid IDs.

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?

Specific verb plus resource ('Get a YouTube video's details'), with an enumerated payload: title, description, channel, duration, view/like counts, publish date, keywords, thumbnails, and a timed transcript. It also scopes accepted inputs (any video link, including Shorts and live streams), so the agent knows exactly what it retrieves and from which URL forms.

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 establishes clear usage context: any YouTube video URL or ID, including Shorts and live streams, with public read-only data. There is no meaningful sibling to route to (tiktok_get_video is a different platform, and no other YouTube tool exists in the list), so the absence of explicit alternatives is a minor gap rather than a real one.

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