Historical world map: states in any year, border history, dated battles, eruptions, quakes.
Scored across 3 tools
Each tool serves a distinct purpose: find_polity for named lookups, search_events for event queries, and world_at_year for temporal geographic queries. There is no overlap in functionality; an agent can easily select the right tool based on whether it needs a specific entity, a set of events, or a snapshot of the world.
All names use lowercase snake_case and clearly describe their action. The first two follow a verb_noun pattern (find_polity, search_events), while world_at_year is a noun phrase with a temporal qualifier. The style is consistent and predictable, though the third name deviates slightly from the verb-first pattern.
With only 3 tools, the server is intentionally focused on querying historical map data. This small surface is appropriate for a niche domain and avoids overwhelming agents, though it leaves room for expansion (e.g., filtering events by type or fetching polity details). The count feels well-scoped rather than insufficient.
The set covers the core queries for a historical map service: entity lookup, event search, and temporal world snapshots. Minor gaps exist, such as a dedicated tool for retrieving a polity's borders at a specific year (find_polity returns all snapshots, which may be excessive). Overall, the surface is complete enough for typical use cases.
Look up a state or empire by name or any of its Wikidata labels and aliases (substring, case-insensitive), or by Wikidata QID. Returns its lifespan, every border snapshot with its bounding box, and links.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Name, e.g. "Ottoman", or a QID, e.g. "Q12560". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden, and it does a solid job: it discloses substring matching, case-insensitivity, acceptance of QIDs, and the specific return contents (lifespan, border snapshots with bounding boxes, links). It does not mention edge cases like empty results or ambiguity, but for a lookup tool the core behavior is transparent.
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 description is one focused, front-loaded sentence. Every clause adds useful information: the target resource, the matching behavior, and the return contents. No filler or repetition exists.
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 lookup tool with no output schema, the description covers both input forms and the key output categories. It could be slightly stronger by noting whether multiple matches can be returned and how they are presented, but nothing critical 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 coverage is 100%, so the baseline is 3, but the description adds meaningful detail beyond the schema: matching is substring and case-insensitive, it covers Wikidata labels and aliases, and QIDs are an accepted form. This helps the agent construct queries correctly.
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 uses a specific verb ('Look up') tied to a clearly defined resource ('a state or empire'), and specifies multiple access paths: name, labels/aliases, or QID. This makes the tool's purpose unambiguous and distinguishes it from the event- and time-oriented sibling 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?
The description makes the main usage context clear: identifying a polity by name or QID. However, it does not explicitly contrast with siblings like search_events or world_at_year, nor does it state when this tool should not be used. Usage is implied rather than explicitly scoped.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search dated map events: battles (Wikidata), UCDP armed-conflict events since 1989, volcanic eruptions VEI 4+ (Smithsonian GVP), significant earthquakes (NOAA), witnessed meteorite falls, and UNESCO World Heritage sites (undated). Results are sorted by year.
| Name | Required | Description | Default |
|---|---|---|---|
| bbox | No | Bounding box [west, south, east, north] in degrees. | |
| layer | No | ||
| limit | No | ||
| query | No | Substring of the event name or detail, e.g. "Vienna". | |
| to_year | No | Year. Negative is BC: -500 = 500 BC. There is no year 0. | |
| from_year | No | Year. Negative is BC: -500 = 500 BC. There is no year 0. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It usefully discloses the result sort order and explicitly flags that UNESCO heritage entries are undated, but it omits how the tool behaves when no layer is selected and whether bbox is effectively required for a spatial search.
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?
One dense, front-loaded sentence supplies the core purpose and then a compact catalog of sources; the final sorting note earns its place. There is no filler or repetition of schema details.
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 multi-source search tool with no annotations and no output schema, the description should say more about result shape and behavior when optional parameters are omitted (especially layer). It covers the searchable content well, but an agent still has to infer default search scope.
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 schema documents bbox, query, and year range, and the description adds value where the schema is weakest: the bare layer enum is enriched with source-specific meaning (UCDP since 1989, VEI 4+, NOAA quakes, etc.). It does not add much to limit or bbox, but the layer coverage is a real contribution.
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 leads with a specific verb and resource ('Search dated map events') and enumerates exactly which event categories and source databases are included. This makes it easy to distinguish from the sibling tools, which deal with polities and world states rather than event lookups.
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 event/source catalog strongly implies this is the tool for historical and geographic event searches, while the sibling names imply non-event tools. However, the description never explicitly states when to use it over find_polity or world_at_year, nor does it mention exclusions or alternatives by name.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the states, empires and cultures whose borders are on the map in a given year (OpenHistoricalMap data), optionally only those overlapping a region.
| Name | Required | Description | Default |
|---|---|---|---|
| bbox | No | Bounding box [west, south, east, north] in degrees. | |
| year | Yes | Year. Negative is BC: -500 = 500 BC. There is no year 0. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool returns entities with borders on the map and optionally filters by region, but it does not specify the output format (e.g., list of names, IDs), whether the operation is read-only (though implied), or any edge cases like handling years with no matches. The description is transparent about the core behavior but lacks detail on output and potential limitations.
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 a single, well-structured sentence that front-loads the primary action and resource, followed by the optional filter. There is no redundant information or filler, and every word contributes to understanding the tool's purpose. It is appropriately sized for the tool's simplicity.
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 the tool has only two parameters, no output schema, and no annotations, the description is reasonably complete. It clearly explains what the tool does and the optional bbox filter. However, it could be improved by stating the expected return format (e.g., a list of names) or clarifying what 'borders are on the map' means precisely, especially for edge cases like incomplete historical data. These are minor gaps, and the description suffices for an agent to call the tool 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?
The input schema already documents both parameters with 100% coverage: year (with BC notation and no year 0) and bbox (bounding box coordinates). The description adds minimal semantic value, merely echoing 'in a given year' and 'overlapping a region,' which essentially restates the schema. Since the schema already covers the parameters, the description does not need to add much, but it also does not provide any additional clarifications beyond what is already known.
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 lists states, empires, and cultures on the map for a given year, with an optional region filter. The verb 'List' and the resource 'states, empires and cultures' are specific, and the OpenHistoricalMap data source adds context. It is distinct from siblings like find_polity (which finds a specific polity) and search_events (which searches events), so an agent can differentiate it without further investigation.
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 no guidance on when to use this tool versus its siblings (find_polity, search_events). It does not mention alternatives or when not to use it. The purpose implies usage for listing historical entities at a specific year, but there is no explicit context or exclusion criteria, leaving the agent to infer when this tool is appropriate.
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_politysearch_eventsworld_at_yearSourced history: 85,753 dated events, each quoted from a citable Wikipedia revision id.
Global earthquake events from the USGS, 2150 BC-present: magnitude, depth, location, counts.
Castles, fortresses, palaces and ruins worldwide: search, nearby, fame ranking, statistics. CC0.
Global tsunami events from NOAA NCEI, 2000 BC-present: wave height, runups, and counts.
Add one secure layer between your agents and this server.