Norwegian dental clinic directory (A2A marketplace). Search ~6,900 clinics by county, specialty, Helfo agreement and emergency availability. 5 tools: tannlege_search, tannlege_info, tannlege_stats, tannlege_akutt, tannlege_kjeder.
Scored across 5 tools
Each tool targets a distinct aspect of the dental clinic directory: emergency duty, full profile, chains, search, and statistics. There is no overlap in functionality.
All tool names follow a consistent pattern: 'tannlege_' followed by a Norwegian noun (akutt, info, kjeder, search, stats), making them predictable and easy to differentiate.
Five tools cover the essential operations for a dental clinic directory: search, details, emergency info, chain listing, and statistics. This is well-scoped and neither too few nor too many.
The toolset covers query, detail, emergency, chains, and stats comprehensively. The only minor gap is a dedicated 'list all clinics' tool, but the search tool with empty query likely serves that purpose.
Find Norwegian dental clinics that offer emergency-duty (akuttvakt) — i.e. treatment outside normal working hours. Optionally filter by county (fylke). Also returns advice about the municipal dental emergency service (kommunal tannlegevakt). Example: 'finn akutt tannlege i Oslo'.
| Name | Required | Description | Default |
|---|---|---|---|
| fylke | No | Limit to clinics in this county. Examples: 'Oslo', 'Vestland' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds context about returning advice on municipal dental emergency service, complementing the annotations without contradiction.
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 three sentences, front-loaded with the main purpose. It is concise and includes an example, though the second sentence about advice is slightly less impact.
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 one optional parameter and no output schema, the description adequately explains the tool's function and additional output (advice). It could benefit from mentioning the return format (e.g., list of clinics), but is sufficiently complete for the tool's 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 input schema has 100% description coverage for the single optional parameter 'fylke', with examples. The description only repeats the filtering option, adding no new semantic information beyond the schema.
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 finds emergency-duty dental clinics in Norway, with optional county filtering. It uses a specific verb ('find') and resource ('emergency-duty dental clinics'), and distinguishes from sibling tools that focus on info, chains, search, or stats.
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 explains when to use the tool (for emergency-duty clinics outside normal hours) and gives an example query. However, it does not explicitly state when not to use it or mention alternative sibling tools, leaving the agent to infer usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch complete profile for a single Norwegian dental clinic by organisation number (org_nr) or internal UUID. Returns name, address, phone, website, Helfo status, emergency duty, specialities, chain affiliation, specialists list, treatments, opening hours, payment options, and profile URL. Example: org_nr '912345678' or id 'uuid-here'.
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | Clinic UUID (alternative to org_nr) | |
| org_nr | No | 9-digit Norwegian organisation number. Example: '912345678' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds value by listing the returned fields (name, address, phone, etc.), providing transparency 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?
The description is concise (3 sentences), front-loaded with purpose, and includes a list of key return fields and examples. No unnecessary words.
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?
Given no output schema, the description enumerates the key fields returned (name, address, Helfo status, etc.), covering all essential aspects for a single clinic fetch. It is complete for the tool's purpose.
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% with good descriptions for both parameters. The description adds examples (org_nr '912345678' or id 'uuid-here'), which aids understanding beyond the schema.
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 verb 'Fetch', the resource 'complete profile for a single Norwegian dental clinic', and the identifier options (org_nr or UUID). It is distinct from sibling tools like tannlege_search (search) and tannlege_stats (statistics).
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 specifies the input parameters (org_nr or UUID) and gives examples, making it clear when to use the tool. However, it does not explicitly state when not to use or contrast with sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all Norwegian dental chains (kjeder) registered on finn-tannlege.com, including the number of clinic locations per chain. Examples of chains: 'Tannhelse Øst', 'Colosseum Tannlege', 'Nordic Dental'. Example question: 'hvilke tannlegekjeder finnes i Norge?'.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate read-only and idempotent behavior. The description adds that it returns a list with clinic location counts, fully disclosing the output. No mention of limitations, but sufficient for this tool.
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?
Two sentences: first states purpose and output, second provides examples. No filler, front-loaded with key information.
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?
Given no parameters or output schema, the description provides sufficient context: what the tool returns, examples, and the domain. Lacks potential details like pagination or sorting, but not necessary for this simple list.
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?
No parameters exist; schema coverage is 100%. Description adds value by explaining what the output includes (chains and clinic counts), though baseline for no params is 4.
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 it lists Norwegian dental chains with clinic locations, gives examples and an example question, and is distinct from sibling tools like tannlege_akutt or tannlege_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 usage for listing chains but does not explicitly state when to use this tool vs siblings. However, sibling names suggest different purposes, providing implicit guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the finn-tannlege.com directory of Norwegian dental clinics. Supports free-text search, county (fylke) filter, specialty filter, Helfo direct-billing filter, and emergency-duty (akuttvakt) filter. Returns clinic name, address, contact info, Helfo status, and profile URL. Example: 'finn kjeveortoped i Bergen med Helfo-avtale'.
| Name | Required | Description | Default |
|---|---|---|---|
| akutt | No | If true, only return clinics with emergency-duty (akuttvakt) | |
| fylke | No | Norwegian county (fylke). Examples: 'Oslo', 'Vestland', 'Rogaland' | |
| helfo | No | If true, only return clinics with Helfo direct-billing agreement | |
| limit | No | Max results (default 10, max 25) | |
| query | No | Free-text search (name or city). Examples: 'Oslo tannklinikk', 'kjeveortoped Bergen' | |
| spesialitet | No | Specialty slug. Examples: 'kjeveortopedi', 'endodonti', 'periodonti' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly, idempotent, openWorld, non-destructive. The description adds return field specifics and filter details, but does not disclose potential rate limits or pagination behavior beyond the limit parameter.
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: three sentences plus an example. It is front-loaded with the primary action and resource, and every sentence adds essential information without fluff.
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?
Given 6 parameters, no required fields, and no output schema, the description adequately covers return values and filter options with an example. Missing minor details like result ordering or pagination hints, but acceptable for completeness.
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 descriptions cover all parameters at 100%. The description adds only a usage example, which is helpful but does not provide new parameter semantics beyond what is in the schema.
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 searches a specific directory with multiple filters and returns structured fields. It distinguishes itself from siblings by being the primary search tool.
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 lists supported search types and filters, giving context on when to use it. However, it does not explicitly exclude cases or mention alternative sibling tools, leaving some ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch aggregated statistics for the Norwegian dental market from finn-tannlege.com. Returns total clinic count, per-county breakdown (per fylke), Helfo count, chain-member count, emergency-duty (akuttvakt) count, and specialist-clinic count. Example question: 'how many dental clinics are there in Norway?'.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds behavioral details beyond annotations, such as the source website (finn-tannlege.com) and the specific statistics returned (total clinics, per-county breakdown, etc.), which is useful context.
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 two sentences: the first states the purpose and source, the second lists the returned statistics. Every sentence adds value, no wasted words.
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?
Given no output schema, the description enumerates all return fields (total clinic count, per-county breakdown, Helfo count, chain-member count, emergency-duty count, specialist-clinic count). This is complete for a simple statistics tool.
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 baseline is 4. The description does not need to explain parameters, and it correctly implies no input is needed.
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 it fetches aggregated statistics for the Norwegian dental market, listing specific counts (total clinics, per-county breakdown, Helfo count, etc.). It differentiates from siblings like tannlege_search (search) and tannlege_akutt (emergency) by being a stats aggregator.
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 provides an example question ('how many dental clinics are there in Norway?') implying when to use the tool. While it does not explicitly state when not to use or name alternatives, the sibling tools list provides context, and the purpose is clear enough for an AI agent.
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.
lokal_discoverlokal_get_producer_affiliationslokal_get_umbrella_memberslokal_infolokal_list_umbrellaslokal_searchlokal_statstannlege_akutttannlege_infotannlege_kjedertannlege_searchtannlege_statslokal_discoverlokal_get_producer_affiliationslokal_get_umbrella_memberslokal_infolokal_list_umbrellaslokal_searchlokal_statstannlege_akutttannlege_infotannlege_kjedertannlege_searchtannlege_statstannlege_akutttannlege_infotannlege_kjedertannlege_searchtannlege_stats
Add one secure layer between your agents and this server.