An artist's measured reach across AI answer engines (which vendors cite them, answer-time vs training) + tracked releases + external demand (Naver + YouTube) with 7d momentum. Measured first-party by KTRENZ.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | Artist slug (from search_kdata), e.g. "rescene". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the full burden of disclosing behavior. It states that the data is 'Measured first-party by KTRENZ' and lists the metrics included, but it does not explicitly state that this is a read-only operation or describe any potential side effects, rate limits, or authentication requirements. It also fails to mention the output structure, though it implies a fetch operation.
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 description is concise—two sentences—and front-loads the primary purpose. It packs significant detail into the first sentence without excessive verbosity. However, the second sentence adds a minor contextual note about measurement source, which is not strictly essential but provides useful info. Overall, efficient and well-structured.
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?
The description covers the scope of what the tool returns (AI answer engine citations, tracked releases, external demand, 7d momentum) but does not specify return format or any behavioral notes like read-only nature. Given the absence of an output schema and annotations, the description leaves some gaps in expectations, particularly around what data format to anticipate.
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?
The input schema provides complete documentation for the single 'slug' parameter (100% coverage), including an example. The description does not add extra meaning beyond the schema, so the baseline of 3 applies; the schema already handles the semantic burden.
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 clearly states the tool's purpose: it retrieves an artist's measured reach across AI answer engines, tracked releases, and external demand. It distinguishes itself from siblings like get_release_reach (focused on releases) and get_trending (likely trending items) by explicitly mentioning 'artist's' and the specific metrics covered, making the purpose unambiguous.
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 the tool is for artist-related metrics and mentions that the slug comes from search_kdata, but it does not explicitly state when to prefer this over alternatives like get_release_reach or get_trending. No exclusions or alternative guidance is provided, so the context is implicit rather than explicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clear, distinct purpose: artist-level reach vs. release-level reach vs. trending velocity vs. entity discovery. The only potential confusion is between get_artist_reach and get_release_reach, but the descriptions clearly separate 'artist's measured reach' from 'a specific release's reach.' An agent could occasionally hesitate between the two reach tools, but the boundaries are well-drawn.
get_artist_reach and get_release_reach establish a clean get_<resource>_reach pattern in snake_case, and get_trending mostly follows the get_ prefix. However, search_kdata introduces a different verb, and get_trending uses a gerund rather than a noun object, so the pattern drifts slightly in the second half of the set.
Four tools is well within the ideal 3-15 range for a focused data-access server. Every tool earns its place: search for discovery, artist reach, release reach, and trending. The scale feels right for a niche K-pop reach-data API — extensible without being bloated.
The domain is well-covered: search resolves entities, then you can fetch artist reach, release reach, or the trending list — a complete read workflow. Minor gap: there's no way to enumerate all releases for an artist independent of what get_artist_reach embeds, but for an analytics read API the surface feels whole.
