Skip to main content
Glama
Sign In

GraphMake

by com.graphmake
OverviewDiscussionsAdmin

Get template fields

get_template
Read-onlyIdempotent

Read one template: its size, description and every editable text and number, as field keys with their current values (e.g. "w0.text": "Annual Report 2026", "w5.datasets.0.values": [820, 1050]). The same keys change the template when it is rendered. With preview set to true, the template's preview image is included.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

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

Input Schema

NameRequiredDescriptionDefault
idYesTemplate id, e.g. "business-stats".
previewNoAlso return the template preview image (default false).

Output Schema

NameRequiredDescriptionDefault
idYes
nameYes
widthYesCanvas width in px.
fieldsYesEvery editable text and number, with the key that changes it.
heightYesCanvas height in px.
categoryYes
previewUrlYesThe template preview image.
descriptionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / id / description
      Previous value: -"Template id from list_templates."New value: +"Template id, e.g. \"business-stats\"."
    • changedOutput schema / properties / fields / description
      Previous value: -"Every editable text and number. Send changed values to render_template by key."New value: +"Every editable text and number, with the key that changes it."
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "category": {
+      "enum": [
+        "business",
+        "education",
+        "marketing",
+        "health",
+        "technology",
+        "general"
+      ],
+      "type": "string"
+    },
+    "description": {
+      "type": "string"
+    },
+    "fields": {
+      "description": "Every editable text and number. Send changed values to render_template by key.",
+      "items": {
+        "properties": {
+          "key": {
+            "description": "Field key, e.g. \"w0.text\" or \"w5.datasets.0.values\".",
+            "type": "string"
+          },
+          "value": {
+            "description": "Current value: text, a number, or a list."
+          },
+          "widget": {
+            "description": "The widget type the field belongs to.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "key",
+          "widget",
+          "value"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "height": {
+      "description": "Canvas height in px.",
+      "type": "integer"
+    },
+    "id": {
+      "type": "string"
+    },
+    "name": {
+      "type": "string"
+    },
+    "previewUrl": {
+      "description": "The template preview image.",
+      "type": "string"
+    },
+    "width": {
+      "description": "Canvas width in px.",
+      "type": "integer"
+    }
+  },
+  "required": [
+    "id",
+    "name",
+    "category",
+    "width",
+    "height",
+    "description",
+    "previewUrl",
+    "fields"
+  ],
+  "type": "object"
+}
  3. 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 (readOnly, idempotent, not open-world), so the description adds genuine extra context: the preview flag's effect and the fact that returned keys are the same ones used at render time. It stops short of noting auth/permission needs or pagination, but it goes beyond the 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?

Three tightly written sentences, front-loaded with the core read action, then return shape with examples, then the optional preview behavior. No filler.

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

Completeness5/5

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

For a simple two-parameter read tool with an output schema and read-only annotations, the description covers purpose, return shape, and the optional preview effect fully. An agent has everything needed to call it correctly.

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

Parameters3/5

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

Schema description coverage is 100% and both parameters are documented there, including preview's default. The description's restatement of preview=true adding the image adds little beyond the schema, so baseline 3 applies.

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?

States a specific verb and resource ('Read one template') and enumerates exactly what is returned — size, description, and every editable text/number as key-value pairs, with concrete examples. This clearly separates it from list_templates and render_template without needing the schema.

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

Usage Guidelines3/5

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

Usage is implied (fetch field keys to inspect or later mutate a template) and the note that 'the same keys change the template when it is rendered' hints at the workflow, but there is no explicit when-to-use, when-not, or sibling routing guidance.

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

All GraphMake 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