datasets_youtube_creators_search

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

With no annotations, the description carries the full burden, and it delivers a critical disclosure: the `_available` flags distinguish a hidden count (stored as 0, *_available: false) from a genuine 0 — preventing a real misinterpretation error. It also discloses data provenance and hydration source, setting expectations about coverage and freshness. It omits rate limits and result envelope details, but the most dangerous ambiguity is handled.

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 sentences with purpose front-loaded first and the caveat placed last. The sort enum list duplicates the schema's sort parameter description, which is mild redundancy, but each sentence otherwise earns its place. For a 22-parameter tool, the length is justified and the structure is easy to scan.

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 22-param search tool with no output schema and no annotations, the description covers the dataset contents, provenance, sort options, and the most error-prone behavioral caveat (_available flags). It does not describe the overall result item shape or pagination behavior beyond what the page_size schema entry already states (page * page_size <= 10000), but the highest-risk semantics are documented.

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. The description adds genuine interpretive value beyond the schema: it explains why the three `*_count_available` filter parameters exist and what a stored 0 means, linking the filter params to the output caveat. The sort enum is redundant with the schema's sort parameter description, but the available-flag semantics go beyond anything 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 ('Search') and a specific resource ('the YouTube creators dataset'), and enumerates exactly what the index contains: subscriber/video/view counts, region, bio, and links. The provenance detail — 'discovered via Common Crawl and Wikidata and hydrated from each channel's public About page' — distinguishes this offline dataset-backed search from live siblings like youtube_channel_search and youtube_search.

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 implies its context of use (searching a pre-built offline index rather than a live API) through the 'search index' and provenance phrasing, but it never names alternatives or states when-not-to-use. An agent must infer the difference between this tool and youtube_channel_search/youtube_search, or between this and the sibling datasets_youtube_creators_item and datasets_youtube_creators_facets. No explicit routing guidance.

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