EaseWeb

Add a slide

add_slide

Add a slide to a presentation you may edit, at the end or at "position" (1-based), optionally with its blocks right away. Returns the new slide with the ids of its blocks.

Input Schema

TableJSON Schema

Name	Required	Description
`h`	No	Canvas height in px (default 720).
`w`	No	Canvas width in px (200-4000, default 1280).
`bg`	No	Background colour, #rrggbb.
`fit`	No	How the background picture fits.
`name`	No	Slide name (at most 30 characters).
`slug`	Yes	The presentation's slug (its address: /movie/<slug>/).
`objects`	No	Blocks of the slide, bottom to top: [{"type": "text"\|"shape"\|"button"\|"line"\|"image"\|"code", "props": {...}}]. Missing props take the presentation theme's defaults (every prop is described in the block format reference). A link to a slide of the same presentation may be given as {"kind": "slide", "slide_number": N}.
`position`	No	1-based place; default: the end.
`background`	No	Background picture: the "src" of an uploaded picture; null removes it.

Output Schema

TableJSON Schema

Name	Required	Description
`h`	No
`w`	No
`bg`	No
`id`	Yes	Stable id of the slide.
`fit`	No
`url`	No	The address people open in a browser.
`name`	No
`number`	Yes	1-based position; changes when slides are reordered.
`objects`	Yes	Blocks, bottom to top.
`background`	No	The "src" of the background picture, or null.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 28, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "background": {
+      "description": "The \"src\" of the background picture, or null.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "bg": {
+      "type": "string"
+    },
+    "fit": {
+      "type": "string"
+    },
+    "h": {
+      "type": "integer"
+    },
+    "id": {
+      "description": "Stable id of the slide.",
+      "type": "integer"
+    },
+    "name": {
+      "type": "string"
+    },
+    "number": {
+      "description": "1-based position; changes when slides are reordered.",
+      "type": "integer"
+    },
+    "objects": {
+      "description": "Blocks, bottom to top.",
+      "items": {
+        "properties": {
+          "id": {
+            "type": "integer"
+          },
+          "props": {
+            "description": "Every prop of the block (see the block format reference).",
+            "type": "object"
+          },
+          "type": {
+            "description": "text, shape, button, line, image or code.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "type",
+          "props"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "url": {
+      "description": "The address people open in a browser.",
+      "type": "string"
+    },
+    "w": {
+      "type": "integer"
+    }
+  },
+  "required": [
+    "id",
+    "number",
+    "objects"
+  ],
+  "type": "object"
+}

First observedSep 28, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the mutation/safety profile is covered. The description adds the useful 'presentation you may edit' permission cue and the fact that the new slide comes back with block ids, but says nothing about permissions required, limits on slide count, or side effects on existing slides.

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

Conciseness4/5

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

Two tight sentences, front-loaded with the verb and resource, with placement and block options following. No filler, though the return-value clause is somewhat redundant against the output schema.

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 9-parameter mutation tool the description plus 100% schema coverage, an output schema, and annotations give an agent everything needed: purpose, placement, optional inline blocks, permission cue, and return shape. No meaningful gap remains.

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%, so every parameter (including the 1-based position and block array shape) is already documented in the schema. The description only restates position semantics and the optional blocks, adding no syntax or constraint detail beyond the schema; baseline 3 is correct.

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

Purpose4/5

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

States a specific verb and resource (add a slide to a presentation) plus the key scope modifiers (end vs. 1-based position, optional inline blocks). It is distinguishable from delete_slide/update_slide/reorder_slides by the verb, though it never names a sibling explicitly.

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?

'at the end or at position' gives placement guidance and 'optionally with its blocks right away' hints you can skip a separate edit_blocks call, but it never states when to prefer this over edit_blocks/update_slide or what preconditions (e.g. edit permission on the presentation) apply.

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

All EaseWeb tools Inspect

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

Need Help?