Public index of YouTube sponsorships: which brands sponsor which creators, from sampled videos.
Scored across 4 tools
Each tool targets a distinct access pattern: get_brand by brand slug, get_creator by YouTube handle, list_categories for taxonomy, and search_sponsorships for filtered discovery. There is slight overlap between get_brand and search_sponsorships when looking up a brand, but the exact-slug vs substring/filter distinction makes the boundaries clear.
Tool names follow a consistent verb_noun pattern: get_ for direct lookup, list_ for enumeration, and search_ for queries. Naming style is uniform with lowercase and underscores.
Four tools is a well-scoped size for a read-only sponsorship index. Each tool covers a core access pattern without redundant additions.
The tool surface covers the main lookup and discovery workflows: by brand, by creator, by category, and by filtered search. Minor gaps like pagination or a full index dump are absent, but agents can still answer typical sponsorship questions.
Every indexed creator a brand has sponsored.
Args:
slug: Brand slug, e.g. 'holafly' (lowercase, hyphen-separated).
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals that only indexed creators are included, but it does not mention whether the result is paginated, what happens for unknown brand slugs, whether it is read-only, or what the response looks like.
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 short and mostly front-loaded with the core meaning, followed by the Args note. The first sentence is slightly awkward grammatically, but it earns its place without unnecessary filler.
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 simple one-parameter tool, the description conveys the main purpose and the required input format. However, with no output schema and no annotations, it stops short of fully describing the return shape or edge-case behavior, so the context is adequate but not rich.
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 0%, but the description compensates by explaining the slug parameter clearly: brand slug, lowercase, hyphen-separated, with a concrete example ('holafly'). This adds useful meaning beyond the bare schema property.
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 states that the tool returns every indexed creator a brand has sponsored, which is a specific resource and scope tied to the brand slug. It is distinguishable from siblings like get_creator and list_categories, though it doesn't explicitly differentiate itself from search_sponsorships.
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?
There is no guidance about when to use this tool versus search_sponsorships or get_creator. The only usage hint is the slug format, which is about parameter input rather than decision-making between alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Every indexed sponsorship for one YouTube creator.
Args:
handle: YouTube handle, with or without the leading '@'.
| Name | Required | Description | Default |
|---|---|---|---|
| handle | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the burden of behavioral disclosure. It clarifies that the result is limited to 'indexed' sponsorships and that the handle may include or omit '@', but it does not disclose return format, pagination, or failure behavior.
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 entire definition is two terse lines. It front-loads the main purpose and keeps the parameter note minimal and relevant.
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 low-complexity single-parameter lookup, the description covers what the tool returns, the required input, and the accepted input format. With no output schema, some return structure detail would strengthen it, but none of the core information needed to call it correctly is missing.
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 0%, and the description compensates by explaining the handle parameter: a YouTube handle with optional leading '@'. This adds real meaning over the schema's bare 'Handle' title, though it stops short of providing an example or normalization behavior.
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 states a clear resource ('one YouTube creator') and scope ('every indexed sponsorship'), which is unambiguous for a getter tool. However, it lacks an explicit verb and does not name any sibling tool to set itself apart.
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?
There is no guidance on when to use this tool over get_brand, list_categories, or search_sponsorships. The only implicit context is that the caller wants sponsorship data associated with a specific creator handle.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
The sponsorship categories in the index, with per-category counts.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It does disclose the return substance: sponsorship categories and their counts. However, it omits behavioral traits such as whether empty categories are included, ordering, pagination, or whether the counts are exact. The disclosure is minimally adequate but not rich.
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?
A single sentence with no waste. It states the resource and the distinguishing output detail immediately. Every word earns its place, and there is no redundant restatement of the tool name.
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 zero-parameter list operation with no output schema, the description is nearly complete: it names the data returned and the counts detail. An agent can invoke it confidently. A fully specified response example or note about category ordering would make it complete, but the absence is minor given the simplicity.
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 tool has zero parameters, so the baseline for this dimension is 4. The description adds no parameter-specific meaning, but none is needed. The phrase 'per-category counts' clarifies what the output conveys, which is more relevant to return semantics than parameter semantics.
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 identifies the resource being listed ('sponsorship categories in the index') and adds the key detail of per-category counts. It distinguishes itself from siblings like get_brand, get_creator, and search_sponsorships by focusing specifically on categories. It lacks an explicit imperative verb like 'lists', but the intent is 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?
There is no guidance on when to use this tool versus the sibling tools, no mention of alternatives, and no stated purpose context such as 'use for faceting or overview'. The agent is left to infer usage solely from the tool name and one-line description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search indexed sponsorships by brand name, category and creator size.
Args:
query: Substring of the brand name (case-insensitive).
category: Category enum value, e.g. 'vpn_privacy' (see list_categories).
min_subscribers: Only creators with at least this many subscribers.
limit: Maximum results (1-200).
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| query | No | ||
| category | No | ||
| min_subscribers | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden, and it uses it well: query is a case-insensitive substring, min_subscribers is a lower bound, limit caps at 200, and 'indexed' hints at a pre-computed dataset. It does not detail return shape or error behavior, but the main filtering semantics are disclosed.
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 one-line summary is front-loaded and the Args block follows a clean, scannable format. Every line adds information; there is no filler or repetition of schema defaults.
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?
All call parameters are fully specified and no output schema exists, so the agent can construct a valid request. Still, the description never states what the tool returns (shape/fields of a sponsorship object) or how multiple filters combine, which are gaps for a tool with no output schema and no annotations.
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 0%, yet every one of the four parameters receives a purpose-specific explanation beyond plain names (e.g., 'case-insensitive', 'only creators with at least', 'maximum results (1-200)'). The category example plus reference to list_categories compensates for missing enum metadata.
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 'Search indexed sponsorships', naming a specific verb, resource, and the three filtering dimensions (brand name, category, creator size). This clearly differentiates it from siblings get_brand/get_creator, which retrieve single entities, and list_categories, which lists enum values.
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 primary use case — searching sponsorships by filters — is clear, and the hint 'see list_categories' tells the agent where to find valid category values. However, it never explicitly contrasts with get_brand/get_creator or states when a direct lookup should be preferred over this search.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_brandget_creatorlist_categoriessearch_sponsorshipsCreator discovery & analytics across YouTube, Instagram, TikTok (30M+) + brand/sponsor intel.
Research YouTube sponsors, inspect sponsorship evidence, and manage brand lists with Sponsorbook.
Search thousands of active YouTube sponsors and 60,000+ channels from any MCP client. Free tier.
Which brands sponsor which gaming creators, with evidence, on YouTube, TikTok, Instagram, Twitch.
Add one secure layer between your agents and this server.
