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

Far beyond the annotations (readOnlyHint, idempotentHint, destructiveHint=false), the description discloses non-obvious behaviors: YouTube rounds subscriber counts above ~1k and the row flags this; the caption content endpoint returns an empty body without a proof-of-origin token and is reported as not_extractable rather than no captions; and calls require an APIFY_TOKEN while no YouTube API key is needed. Nothing contradicts the annotations — 'Read only' actually reinforces readOnlyHint.

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?

The core purpose and return values are front-loaded in the first sentence, and every subsequent sentence carries a unique, essential caveat (rounding, transcript gating, auth/credits). At roughly 170 words it is longer than average, but there is no padding — each sentence earns its place by preventing a wrong interpretation.

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 to lean on, the description spells out the return payload and its quirks, the two resolution modes, the optional transcript behavior and its failure mode, and the auth/cost profile — everything an agent needs to invoke the tool correctly. The 7 optional parameters are fully handled by the schema, so no gap remains.

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?

All 7 parameters are documented at 100% coverage in the input schema with rich descriptions (handle 'skips discovery,' skipCache's 7-day caching, transcriptVideoCount as the 'billable transcript event' dial). The description itself adds little parameter-level detail beyond framing the domain-vs-handle choice, which the schema already states, so it sits at the high-coverage baseline of 3.

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?

The description opens with a specific verb phrase — 'Resolve a company domain, or a YouTube handle, to that company's YouTube channel' — and enumerates the exact return fields (subscriber count, UC channel id, channel name, creation date, description). With no sibling tools to differentiate from, the specificity alone removes any ambiguity about what the tool does.

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 frames the two supported lookup paths (domain vs handle) and clarifies which skips discovery, plus gives cost-aware guidance: transcripts are 'the expensive half' and each call 'consumes Apify credits.' It does not name exclusions or alternatives, but since no sibling tools exist there is nothing to exclude against.

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