Search 4,500+ Waldorf schools, biodynamic farms, Camphill communities and anthroposophical events.
Scored across 4 tools
The tools have mostly distinct purposes: proximity search, filtered directory search, detail lookup, and event listing. There is some potential overlap between find_nearby and search_directory when a user wants organizations in a location, but the descriptions make the intended boundaries fairly clear.
The set mixes conventions: get_listing and search_directory follow verb_noun, find_nearby uses a verb plus adverb rather than a noun object, and upcoming_events is adjective_noun with no verb. The names remain readable, but the pattern is not fully consistent.
Four tools is a well-scoped surface for a read-only directory and events server. Each tool supports a distinct workflow: search, proximity lookup, detail retrieval, and event discovery.
Directory coverage is solid: search, nearby lookup, and full listing details cover the core lifecycle. The events side is thinner, lacking an event-detail tool or filtering, but agents can likely work around this from the upcoming_events results.
Find anthroposophical organizations closest to a point, sorted by distance. Use the latitude and longitude of a town or address.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many results to return (default 15, max 50) | |
| category | No | waldorf = Waldorf/Steiner schools and kindergartens; biodynamic = biodynamic and Demeter farms; christian_community = The Christian Community congregations; camphill = Camphill communities; community = other intentional communities; eurythmy = eurythmy and the arts; medicine = anthroposophic medicine; societies = Anthroposophical Society branches and study groups; eldercare = care homes; online = online resources; social_media = groups and channels; science = Goethean science | |
| latitude | Yes | ||
| longitude | Yes | ||
| radius_km | No | Search radius in kilometres (default 50, max 500) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely new behavior — results are sorted by distance — but says nothing about what happens when nothing is within radius_km, whether radius is silently widened, or what fields come back.
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 short sentences, zero waste, with the core capability front-loaded before the input hint. Nothing is padded or restated from the title.
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 leaves the return shape unexplained — an agent cannot tell whether results include distance, address, or contact details. For a 5-parameter geo search this is adequate but clearly thin.
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 60%: limit, category and radius_km carry their own descriptions, while latitude/longitude are undocumented in the schema and only loosely covered by 'the latitude and longitude of a town or address'. The description adds no semantics for category or radius, so it does not compensate for the gap but doesn't need to.
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 ('Find anthroposophical organizations') plus the result ordering ('closest to a point, sorted by distance'), which separates it from text-oriented siblings like search_directory and get_listing. It never names a sibling explicitly, so the differentiation is inferred from the geo-proximity framing rather than stated.
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?
'Use the latitude and longitude of a town or address' hints at the intended input workflow but is really an input hint, not usage guidance. There is no statement of when to prefer this over search_directory or get_listing, and no exclusion such as 'do not use for name lookups'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Full public details of one directory listing by its id (from search_directory or find_nearby).
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | The listing id (a UUID) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior. The description adds that this returns full public details and that the id comes from search results, but it does not describe error behavior, response shape, or rate limits. With annotations carrying the safety profile, this is adequate.
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?
It is a single front-loaded sentence with no wasted text. The essential scope and id source are stated immediately.
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 read-only lookup, the description, schema, and annotations together are nearly complete. The only minor gap is that it does not mention behavior when the id is not found, but that is not critical for this tool type.
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 id parameter is already documented as a UUID. The description adds useful provenance by specifying that the id should come from search_directory or find_nearby, which helps the agent supply a valid value.
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 names a specific verb-resource pair: retrieving full public details of one directory listing by id. It also ties the id back to search_directory or find_nearby, which distinguishes this tool from the sibling search tools.
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?
It clearly tells the agent to use an id obtained from search_directory or find_nearby, giving a concrete usage context. It does not explicitly state when not to use it, but the sibling relationship is clear enough for routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search Sophia Commons for anthroposophical organizations: Waldorf schools, biodynamic farms, Camphill communities, The Christian Community, clinics, eurythmy, study groups and more. Combine a free-text query with category, country and city filters.
| Name | Required | Description | Default |
|---|---|---|---|
| city | No | City or town name | |
| limit | No | How many results to return (default 20, max 50) | |
| query | No | Words to look for in the name or description, e.g. "kindergarten", "Demeter dairy", "Goetheanum" | |
| country | No | Country name in English, e.g. "Germany", "United States", "New Zealand" | |
| category | No | waldorf = Waldorf/Steiner schools and kindergartens; biodynamic = biodynamic and Demeter farms; christian_community = The Christian Community congregations; camphill = Camphill communities; community = other intentional communities; eurythmy = eurythmy and the arts; medicine = anthroposophic medicine; societies = Anthroposophical Society branches and study groups; eldercare = care homes; online = online resources; social_media = groups and channels; science = Goethean science |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered structurally. The description adds no behavioral context beyond that — no note on result ordering, match semantics (substring vs fuzzy), or what an empty result means — so with annotations present a 3 is appropriate.
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 with zero filler: the scope and covered entity types come first, then the filtering mechanic. Every clause earns its place and nothing is repeated from structured fields.
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 five optional parameters all documented in the schema, full annotations, and no output schema, the description covers what an agent needs to invoke the tool. It stops short of describing result shape or match behavior, but that gap is modest given the rich schema.
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%, and the category enum is thoroughly documented inline including per-value meanings. The description only echoes that query and filters can be combined, adding nothing the schema does not already contain, 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?
States a specific verb (search) plus the resource (Sophia Commons directory) and enumerates the entity types covered, so an agent can immediately tell this is a filtered directory lookup. It does not explicitly contrast itself with get_listing or find_nearby, so sibling differentiation is only inferable from the filtering language.
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 second sentence explains how to combine a free-text query with category/country/city filters, which implies usage. However, it never says when to prefer this over find_nearby (proximity) or get_listing (single record), nor any exclusions, so routing guidance is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Upcoming anthroposophical events listed on Sophia Commons: conferences, courses, talks, festivals, workshops and online study groups, soonest first.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many results to return (default 20, max 50) | |
| query | No | Words to look for in the title, description or organizer | |
| country | No | Country name in English | |
| days_ahead | No | How far ahead to look (default 90 days) | |
| online_only | No | Only online events |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare this as a safe, read-only, idempotent, non-destructive operation. The description adds useful behavioral context: the data source, the content categories covered, and the 'soonest first' ordering.
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 that identifies the tool's scope, source, event types, and ordering without wasted text.
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 is largely complete for a 5-parameter read-only list tool: annotations cover safety, the schema covers parameters, and the description covers source, scope, and ordering. It does not describe the return shape, which is a minor gap given there is no output schema.
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%, so all five parameters are fully documented in the schema. The description does not add parameter-specific meaning beyond implying temporal ordering; baseline 3 applies when the schema carries this 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 states a specific resource ('Upcoming anthroposophical events') and names the source ('Sophia Commons'), along with event categories and ordering. It does not explicitly differentiate this tool from siblings like find_nearby or search_directory, so it stops short of a 5.
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: this is for browsing upcoming events, soonest first. There is no explicit when-to-use guidance, no mention of alternatives such as find_nearby or search_directory, and no exclusions.
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.
find_nearbyget_listingsearch_directoryupcoming_eventsContact Improvisation events, teachers, venues and communities worldwide. Read-only.
Search and discover local community listings, classifieds, services and events.
Find a birth, postpartum or end-of-life doula near you.
Search Artsdata for authoritative data on Canadian events, artists, organizations, and places.
Add one secure layer between your agents and this server.
