Skip to main content
Glama

What3words

by io.github.pipeworx-io

Autosuggest

autosuggest
Read-onlyIdempotent

Given a partial / mistyped 3-word input, return ranked suggestions. Optional focus point biases results toward proximity.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
inputYesPartial three-word string
countryNoRestrict to ISO country code(s), comma-separated
languageNo2-letter language
n_resultsNo1-100 (default 3)
focus_latitudeNoBias toward this latitude
focus_longitudeNoBias toward this longitude

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countYesNumber of suggestions returned
inputYesThe partial 3-word input submitted
suggestionsYesList of ranked suggestions

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "input": "filled.count.so"
+  },
+  {
+    "country": "GB",
+    "focus_latitude": 51.520847,
+    "focus_longitude": -0.195521,
+    "input": "index.home",
+    "n_results": 5
+  }
+]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "count": {
+      "description": "Number of suggestions returned",
+      "type": "number"
+    },
+    "input": {
+      "description": "The partial 3-word input submitted",
+      "type": "string"
+    },
+    "suggestions": {
+      "description": "List of ranked suggestions",
+      "items": {
+        "properties": {
+          "country": {
+            "description": "Country containing the suggestion",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "distance_to_focus_km": {
+            "description": "Distance in km from focus point if provided",
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "language": {
+            "description": "Language code of the suggestion",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "nearest_place": {
+            "description": "Nearest place to the suggestion",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "rank": {
+            "description": "Ranking of the suggestion",
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "words": {
+            "description": "The suggested 3-word address",
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "input",
+    "count",
+    "suggestions"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

A4.4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds that the tool returns ranked suggestions and can bias by location. This additional context is valuable but does not contradict annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: two sentences, no unnecessary words. The main action is front-loaded, and every word contributes value. Ideal structure for an AI agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema (not shown here), the description does not need to explain return values. It covers the input and optional behavior. It lacks mention of error handling or edge cases, but for a straightforward suggestion tool, this is sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description adds meaning: 'partial / mistyped 3-word input' clarifies the input parameter, and 'optional focus point biases results toward proximity' adds context to focus_latitude/focus_longitude. This exceeds the minimal schema documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: it returns ranked suggestions for partial or mistyped 3-word input. It also mentions the optional focus point parameter for proximity bias. This distinguishes it from siblings like 'words_to_coords' (exact conversion) and 'coords_to_words'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context: use when input is partial or mistyped, optionally with a focus point. It provides clear context but does not explicitly state when not to use this tool or name alternatives. Given sibling tools, the context is sufficient for an agent to infer appropriate use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All What3words toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation2/5

There is significant overlap among the meta-query tools: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, discover_tools, suggest_questions, and validate_claim all route to the same underlying data catalog with only subtle differences in grounding or scope. Company-focused tools like entity_profile, compare_entities, recent_changes, and resolve_entity also share fuzzy boundaries. The four what3words tools are clearly distinct, but they sit awkwardly beside a much larger, partially redundant Pipeworx/prediction-market cluster.

Naming Consistency3/5

All tool names use snake_case, which provides a base level of consistency, but the naming patterns vary widely: some are verb_noun (list_languages, recall, forget), some are X_to_Y (coords_to_words, words_to_coords), some are brand-prefixed (pipeworx_*, polymarket_*), and some are bare concepts (deep_research, entity_profile, autosuggest). The ask_pipeworx family is internally consistent, as are the polymarket_* tools, but the overall set lacks a single predictable convention.

Tool Count2/5

35 tools is well above the 25-tool threshold, and the server is named What3words when only 4 of the 35 tools actually belong to that geocoding domain. Even interpreted as a general data platform, 35 tools with a heavily overlapping meta-tool layer feels bloated rather than well-scoped. The what3words-specific surface would be appropriately sized at 4-5 tools on its own.

Completeness3/5

For what3words specifically, the surface is complete: coords_to_words, words_to_coords, autosuggest, and list_languages cover the core bidirectional conversion plus discovery. However, for the broader domain the server actually serves, there are notable gaps such as no direct resolve-by-pipeworx://-URI tool and no open-web search, despite citations and external data being advertised as fetchable. The mix of geocoding, data lookup, prediction markets, memory, and subscriptions makes it unclear what complete coverage would even mean.

Resources