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

The description is otherwise unusually candid — YouTube's subscriber rounding, the transcript gating and the not_extractable vs. no-captions distinction, credit consumption, and the APIFY_TOKEN requirement are all disclosed. However, it asserts 'Read only' while the annotations declare readOnlyHint=false, an outright conflict on the safety profile. Flagged as an annotation contradiction, which caps this score.

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?

Purpose and return shape are front-loaded, and the caveats (rounding, gating, status field, cost) follow in descending priority. It runs long at roughly nine sentences, and the aside about the package name is borderline, but almost every sentence carries information an agent needs.

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 8 optional parameters and no output schema, the description does the heavy lifting: it names the return fields, the flat-row shape, the youtube_status signal, and the not_found case, plus auth and billing. It stops short of enumerating all possible youtube_status values or how a missing domain+handle is handled, which keeps it from a 5.

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 adds genuine semantics beyond it: transcripts are CURRENTLY GATED by YouTube and the row reports not_extractable rather than no-captions, which materially changes how an agent should interpret includeTranscripts/transcriptVideoCount results. It also explains the cost framing of a transcript run rather than leaving it to the schema.

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?

Opens with a precise verb+resource: resolve a domain or handle to a company's YouTube channel, then lists the returned fields (subscriber count, UC id, name, creation date, description). It also explicitly fences the scope — 'it does not search YouTube, list a channel's videos, or return video detail' — so an agent knows exactly what this tool is and is not.

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 direct usage guidance: 'Use it to look up one known company channel per call', with explicit exclusions (no search, no video listing, no video detail) and a sequencing rule ('Read youtube_status before any count'). The domain-vs-handle choice and its consequence (full discovery vs. straight to fetch) is stated inline.

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