Skip to main content
Glama

Opencages

by io.github.pipeworx-io

Reverse

reverse
Read-onlyIdempotent

Reverse-geocode a latitude/longitude pair to a human-readable address using OpenCage (requires API key); returns formatted address, country, city, postcode, and timezone.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
latYes
lonYes
abbrvNo
languageNo
no_annotationsNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
rateNoRate limit information
statusNoAPI response status
resultsNoArray of reverse geocoding results
total_resultsNoTotal number of results found

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: +[
+  {
+    "lat": 48.8566,
+    "lon": 2.3522
+  },
+  {
+    "language": "en",
+    "lat": 40.7128,
+    "lon": -74.006
+  }
+]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "description": "Response from OpenCage reverse geocoding API",
+  "properties": {
+    "rate": {
+      "description": "Rate limit information",
+      "properties": {
+        "limit": {
+          "description": "Request limit",
+          "type": "integer"
+        },
+        "remaining": {
+          "description": "Remaining requests",
+          "type": "integer"
+        },
+        "reset": {
+          "description": "Reset timestamp",
+          "type": "integer"
+        }
+      },
+      "type": "object"
+    },
+    "results": {
+      "description": "Array of reverse geocoding results",
+      "items": {
+        "properties": {
+          "annotations": {
+            "description": "Additional annotations (if no_annotations not set)",
+            "type": "object"
+          },
+          "bounds": {
+            "description": "Bounding box coordinates",
+            "type": "object"
+          },
+          "components": {
+            "description": "Address components breakdown",
+            "type": "object"
+          },
+          "confidence": {
+            "description": "Confidence score 0-10",
+            "type": "integer"
+          },
+          "formatted": {
+            "description": "Formatted address string",
+            "type": "string"
+          },
+          "geometry": {
+            "description": "Geographic coordinates",
+            "properties": {
+              "lat": {
+                "description": "Latitude",
+                "type": "number"
+              },
+              "lng": {
+                "description": "Longitude",
+                "type": "number"
+              }
+            },
+            "type": "object"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "status": {
+      "description": "API response status",
+      "properties": {
+        "code": {
+          "description": "HTTP status code",
+          "type": "integer"
+        },
+        "message": {
+          "description": "Status message",
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "total_results": {
+      "description": "Total number of results found",
+      "type": "integer"
+    }
+  },
+  "type": "object"
+}
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already indicate readOnly, idempotent, and non-destructive behavior. The description adds that it uses an external API (OpenCage) and requires an API key, which is beyond annotation info. It does not mention rate limits or potential errors, but overall adds 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.

Conciseness5/5

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

The description is a single sentence that is action-front-loaded, providing the core purpose, dependencies, and key output fields. No extraneous words.

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

Completeness3/5

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

An output schema exists but is not detailed here. The description covers the main inputs and outputs but omits explanation of optional parameters. Given the tool has 5 parameters and 0% schema coverage, the description is incomplete for full parameter understanding.

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

Parameters2/5

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

Schema coverage is 0%, so the description must compensate. It explains the input lat/lon and lists return fields, but does not describe the optional parameters (abbrv, language, no_annotations). This leaves the agent without understanding the optional parameters' meaning.

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 performs reverse geocoding (converting lat/lon to address) using OpenCage. It specifies the tool's action, resource, and distinguishes from sibling 'geocode' which is forward geocoding.

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 mentions 'requires API key,' indicating a prerequisite. The sibling list includes 'geocode,' implying this is for reverse geocoding. However, it does not explicitly state when to use or when not to use this tool versus alternatives, leaving some ambiguity.

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

All Opencages 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
Disambiguation3/5

Several tools occupy adjacent territory—ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research, and validate_claim all answer natural-language questions, and the Polymarket family has five overlapping analysis tools. The descriptions do a decent job of differentiating them, but an agent could still plausibly select the wrong variant in a mixed workflow.

Naming Consistency3/5

Most names follow a readable lowercase snake_case style, and there are coherent families like ask_pipeworx_*, polymarket_*, and pipeworx_*. However, conventions are mixed across the set—some are verb_noun (list_subscriptions, resolve_entity), some are bare verbs (forget, recall, reverse), and some are noun-phrase-only (entity_profile, recent_alerts)—so no single predictable pattern governs the whole server.

Tool Count2/5

33 tools is well past the 25+ threshold for a heavy tool surface, even accounting for the broad data-domain ambitions of the server. Many of these tools are meta-tools or thin variants of one another, so the set feels larger than necessary and imposes meaningful selection cost on an agent.

Completeness4/5

The server covers its apparent domain thoroughly: querying, grounded verification, deep research, entity resolution, profiles, comparisons, change tracking, claim validation, memory, subscriptions, and prediction-market analytics are all represented. Minor gaps exist—such as no direct tool for retrieving a raw pipeworx:// citation record and no account/auth flow—but agents can generally complete core workflows without dead ends.

Resources