Skip to main content
Glama

Local MCP

by com.local-mcp
OverviewDiscussionsAdmin

PowerPoint Create

ppt_create

Creates a PowerPoint presentation (.pptx) at path from an array of slides, each {title, bullets:[…]}. Requires confirm=true — called without it, returns a preview of the deck instead of writing the file. The path must be somewhere Local MCP can write; Desktop/Documents/Downloads may need a one-time Files-and-Folders grant (System Settings → Privacy & Security → Files and Folders). Returns {created, path, slides}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYesOutput path for the .pptx file
slidesYesArray of slide OBJECTS, each with a title and optional bullets
confirmNoMust be true to create

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYesPath of the created .pptx file
slidesYesNumber of slides created
createdYesTrue when the file was created

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / slides / description
      Previous value: -"Array of {title, bullets:[]} slide objects"New value: +"Array of slide OBJECTS, each with a title and optional bullets"
    • addedInput schema / properties / slides / items
      Added value: +{
+  "properties": {
+    "bullets": {
+      "description": "Bullet lines",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "title": {
+      "description": "Slide title",
+      "type": "string"
+    }
+  },
+  "required": [
+    "title"
+  ],
+  "type": "object"
+}
  2. Changed2 schema fields changed
    • changedInput schema / properties / slides / description
      Previous value: -"Array of slide OBJECTS, each with a title and optional bullets"New value: +"Array of {title, bullets:[]} slide objects"
    • removedInput schema / properties / slides / items
      Removed value: -{
-  "properties": {
-    "bullets": {
-      "description": "Bullet lines",
-      "items": {
-        "type": "string"
-      },
-      "type": "array"
-    },
-    "title": {
-      "description": "Slide title",
-      "type": "string"
-    }
-  },
-  "required": [
-    "title"
-  ],
-  "type": "object"
-}
  3. Changed2 schema fields changed
    • changedInput schema / properties / slides / description
      Previous value: -"Array of {title, bullets:[]} slide objects"New value: +"Array of slide OBJECTS, each with a title and optional bullets"
    • addedInput schema / properties / slides / items
      Added value: +{
+  "properties": {
+    "bullets": {
+      "description": "Bullet lines",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "title": {
+      "description": "Slide title",
+      "type": "string"
+    }
+  },
+  "required": [
+    "title"
+  ],
+  "type": "object"
+}
  4. First observed

TDQS

A4.7/5.0
Behavior5/5

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

With all annotations false (no readOnly/destructive hints), the description carries the full disclosure burden — and delivers. It reveals the non-obvious two-phase behavior (confirm=true or only a preview is returned), the Files-and-Folders permission prerequisite for certain paths, and the return shape. No contradiction with 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 sentences, purpose front-loaded, with each sentence earning its place: purpose and input shape, confirm/preview behavior, then permissions and return values. The return-format note slightly duplicates the existing output schema but costs only a few words.

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 write-mutation tool with zero safety annotations, the description covers everything an agent needs to invoke it correctly: purpose, slide input structure, the confirmation gate, and write-location permissions. Only minor gaps remain (overwrite behavior, .pptx extension handling), which don't block correct use.

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 covers all 3 parameters at 100%, so baseline is 3. The description adds genuine value by explaining what confirm=false actually does (returns a preview of the deck instead of writing), which enriches the schema's terse 'Must be true to create' and clarifies the optional-but-necessary nature of confirm.

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 (Creates), a specific resource (PowerPoint .pptx), and the exact input structure (array of slides with {title, bullets}). The explicit 'PowerPoint' naming cleanly separates it from file-writing siblings like excel_create, word_create, and from reading counterparts like ppt_read.

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 purpose is unambiguous enough that when-to-use is self-evident, and the 'Requires confirm=true' instruction functions as a clear usage condition with its consequence (preview instead of write). However, no sibling alternatives are named and there is no explicit when-not-to-use, so it falls short of a 5.

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

All Local MCP 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