Skip to main content
Glama
Sign In

Postfjord

by com.postfjord
OverviewDiscussionsAdmin

Get analytics

postfjord_get_analytics
Read-only

How the workspace is doing, the numbers the Analytics screen shows: per channel followers and change, posts, likes and comments, per post and as a rate of followers, reach where the platform shares it; the top posts across channels with their text and link; and the best weekday and hour to post (in the workspace time zone, measured against each channel's usual). days is 7, 30, 90 or 365 (default 30), cut to what the plan keeps. Read notes for what is missing and why. Use it to answer what performed and to plan posts like the ones that did.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "postfjord_get_analytics"
  }
}

Input Schema

NameRequiredDescriptionDefault
daysNo7, 30, 90 or 365. Any other number uses the nearest of these.

Output Schema

NameRequiredDescriptionDefault
daysNo
notesNo
totalsNo
channelsNo
topPostsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • removedInput schema / properties / days / anyOf
      Removed value: -[
-  {
-    "const": 7,
-    "type": "number"
-  },
-  {
-    "const": 30,
-    "type": "number"
-  },
-  {
-    "const": 90,
-    "type": "number"
-  },
-  {
-    "const": 365,
-    "type": "number"
-  }
-]
    • addedInput schema / properties / days / description
      Added value: +"7, 30, 90 or 365. Any other number uses the nearest of these."
    • addedInput schema / properties / days / type
      Added value: +[
+  "number",
+  "string"
+]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "properties": {
+    "channels": {
+      "items": {
+        "additionalProperties": {},
+        "properties": {
+          "channelId": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "platform": {
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "days": {
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "notes": {
+      "anyOf": [
+        {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "topPosts": {
+      "items": {
+        "additionalProperties": {},
+        "properties": {},
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "totals": {
+      "additionalProperties": {},
+      "properties": {},
+      "type": "object"
+    }
+  },
+  "type": "object"
+}
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover the safety profile (read-only, non-destructive, closed-world), and the description adds real behavior beyond them: results are cut to what the plan keeps, a notes field explains what is missing and why, weekday/hour is in workspace time zone and measured against each channel's usual, and reach is only present where the platform shares it. These caveats prevent an agent from misreading absent data as zero performance.

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

Conciseness3/5

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

The purpose is front-loaded, but the tool is described in one long semicolon-chained run-on that mixes return contents, parameter rules, caveats, and usage advice. Every element is relevant, yet the dense packing makes it harder to scan than a short structured split would be.

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 and the description still explains the payload shape well, and the single parameter's behavior is covered. What remains thin is guidance on the tool's boundaries relative to the many sibling get_* tools, which the agent must infer.

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 coverage is 100% and the schema already lists the 7/30/90/365 values with nearest-match snapping, so the description mostly restates it. It does add value the schema lacks: the default of 30 and the fact that the window is truncated to what the plan retains, which affects how the agent interprets the response.

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 enumerates exactly what the tool returns: per-channel followers and change, posts, likes, comments, rates of followers, reach where available, top posts with text and link, plus best weekday and hour. That is a specific verb-plus-resource statement an agent can match to a request without opening the schema, and it is clearly distinct from the sibling get_* tools that return single posts, campaigns, or profiles.

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?

It states a use case plainly: answer what performed and plan posts like the ones that did, and directs the agent to read notes for what is missing. There is no explicit when-not guidance or named alternative sibling, but the intended context is unambiguous.

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

All Postfjord toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources