Read-only: which LLM is best in 7 languages (zh, ko, nb, de, nl, es, pt), from public benchmarks.
Scored across 3 tools
The three tools have clearly distinct purposes: retrieving top picks for a language, listing supported languages, and listing paid products. There is no overlap in functionality, so an agent can easily select the right tool.
All tool names use snake_case with a consistent verb_noun pattern (get_*, list_*). The verbs are standard and predictable, making the naming highly consistent.
With only 3 tools, the server is minimal but each tool serves a distinct purpose. While it's on the lower end of the typical range, it is not excessively thin for a simple informational board.
The tools cover the core board functionality: discovering languages, getting top picks, and accessing products. Minor gaps exist, such as no tool to retrieve all top picks in a single call or to get detailed benchmark/model information.
Free: the board's current top LLM pick and best open-weights pick for one language, with the public benchmark source it is based on.
| Name | Required | Description | Default |
|---|---|---|---|
| lang | Yes | Language code: zh, ko, nb, de, nl, es or pt |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so safety is covered. The description adds real context beyond that: the call is 'Free', it covers one language, and it returns two distinct picks plus the public benchmark source they are based on. It does not contradict the annotations, and no permission or rate-limit caveats are mentioned (nor likely needed for a read-only lookup).
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 front-loaded sentence leads with the cost signal ('Free') and then the return contents; nothing is redundant or padded. Slightly dense, but every clause earns its place.
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 one-parameter, read-only lookup with no output schema, the description usefully previews the return contents (top LLM pick, best open-weights pick, benchmark source), which is the main thing an agent needs. What is missing is a note on how the 'free' tier relates to any paid alternative, and the unstated (but low-risk) behavior when a language has no pick.
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 100% — the lang parameter's schema entry already enumerates the accepted language codes (zh, ko, nb, de, nl, es, pt). The description only restates 'for one language' and adds no syntax, default, or constraint beyond the schema, so the baseline 3 applies.
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 gives a clear verb+resource ('get ... top pick') and goes further by naming the exact return contents: the top LLM pick, the best open-weights pick, and the benchmark source. Sibling tools (list_languages, list_products) are enumeration tools with obviously different purposes, so no explicit differentiation is required. A minor ambiguity remains about what 'the board' refers to.
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?
Usage is only implied: the caller infers it should call this tool when it needs the leading model for a single language, and 'Free:' hints that this is the no-cost path. There is no explicit when-to-use, when-not-to-use, or named alternative (e.g., a paid/pro tier).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the 7 languages covered by the Polyglot AI Board with their codes.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so safety is covered. The description adds value beyond that by disclosing the result shape (exactly 7 languages, each with a code), which matters because there is no output schema.
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 front-loaded sentence with no filler; the count and the inclusion of codes are the two facts an agent needs, and both are stated compactly.
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-param, read-only list tool with no output schema, the description covers what is returned and how many items, which is enough to call and interpret it. Minor remaining gap is the exact code format, which is not specified.
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 takes zero parameters, so the baseline is 4; there is nothing for the description to clarify about inputs, and it correctly stays silent on them.
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 (List) and resource (languages covered by the Polyglot AI Board) and adds the useful detail that results include language codes. It is clearly distinct from siblings like get_top_pick and list_products. It stops short of 5 only because it doesn't explain what the languages are used for.
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?
Usage is implied: an agent wanting valid language codes would call this, and there are no competing siblings to route between. However, there is no explicit when-to-use statement or note about when another tool would be preferable.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Paid data packs for agents (model picker, eval suites, false friends, per-language packs) with prices and Vermarco buy links, plus the x402 pay-per-call API.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already covers safety. The description adds that results include paid packs, prices, Vermarco buy links, and x402 API, but it does not describe ordering, pagination, or response shape, so it adds useful but limited context beyond annotations.
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?
Single front-loaded sentence with no filler; the parenthetical enumerates pack types efficiently. It could be slightly sharper with an explicit list verb.
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-param read-only list with no output schema, the description conveys the category, included data (prices, buy links, API), and product types. It leaves whether all products are returned and how siblings differ implicit.
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?
Zero parameters, so no parameter semantics are required; baseline 4 applies. The description cannot and need not add parameter detail.
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?
Names the resource as paid data packs for agents and enumerates the included product categories, prices, buy links, and x402 API, so the agent can tell what product catalog this exposes. It lacks an explicit verb and does not contrast with get_top_pick or list_languages, so it is clear but not sibling-differentiated.
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?
Provides no when-to-use guidance, prerequisites, or alternatives. The agent must infer that this returns the full catalog from the product enumeration; siblings get_top_pick and list_languages are not mentioned.
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_top_picklist_languageslist_productsLLM rankings from public benchmarks, model comparisons and source-linked results. Updated daily.
Daily Scandinavian AI benchmark — Norwegian, Swedish, Danish. 12+ models tested.
Independent test scores for open-weight LLMs: best model for your GPU or Mac, comparisons.
Independent measurements of how 12 AI models answer brand questions in Chinese and English.
Add one secure layer between your agents and this server.