Search key figures for Norway's 357 municipalities: taxes, fees, population, schools, elections.
Scored across 1 tool
There is only one tool, so there is no possibility of selecting the wrong one or confusing overlapping purposes. Its purpose (site content search) is stated clearly and unambiguously.
The single tool 'search_site' follows a clean verb_noun convention. With only one tool there is no cross-tool inconsistency to penalize.
A dedicated website-search server legitimately needs only one search entry point, so the narrow surface fits the scope. It is slightly thin (no companion fetch/get-page tool), but it is not a mismatch.
Search is the core purpose and is fully covered, returning url, title, snippet and score. Minor gap: there is no tool to retrieve or expand a full page from a returned URL, and no way to enumerate the site's content, but agents can work around this with the snippets.
Search the content of this website. The content is Norwegian (bokmål), so write the query in Norwegian, as a short question or keywords, for example "eiendomsskatt Bergen" or "hvor mange barnehager er det i Tromsø?". Words are matched on their stems. Returns the best-matching pages as url, title, snippet and score.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of results (default 5). | |
| query | Yes | What to look for, in Norwegian. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does reasonably well: it discloses the corpus language, that matching is stem-based, and the exact shape of results (url, title, snippet, score). It is silent on auth/rate limits, but for a read-only search that omission is minor.
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 tight sentences, front-loaded with purpose, then the language/query constraint, then the return contract. The examples are short and directly operational; nothing is 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?
With no output schema, the description explicitly covers the return fields, and it covers the input constraint that matters most (query language and phrasing) plus the default result behavior. An agent has everything needed to call it correctly.
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, but the description earns more by explaining the query in terms the schema does not: natural-language question form, Norwegian language requirement, and stem matching. It adds meaning beyond the schema's terse "What to look for, in Norwegian."
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 and resource (search the content of this website) and clearly bounds the corpus, distinguishing it from a general web search. It also names what comes back (best-matching pages), so an agent knows exactly what this tool does before reading the schema.
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?
Gives explicit, actionable usage guidance: the query must be written in Norwegian (bokmål), as a short question or keywords, with two concrete examples. It does not state exclusions or alternatives, but with no sibling tools there is little to exclude against.
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.
search_siteFinancial data, credit scores, and economic indicators for 14,800+ U.S. municipalities.
Finnish postal-area and municipality statistics; rank, compare, history, air quality, nearby places
Read-only German federal election results for municipalities, with harmonized geography.
Norway's company register (Enhetsregisteret) for AI: lookup, search, name resolution, key financials
Add one secure layer between your agents and this server.
