EaseWeb

Leave a note

add_comment

Leave a note on any presentation you can see -- on a slide ("slide_id") or on the whole presentation -- or answer a thread ("reply_to"). The owner of the presentation sees the note in the viewer; the thread is seen by the owner and by whoever started it.

Input Schema

TableJSON Schema

Name	Required	Description
`slug`	Yes	The presentation's slug (its address: /movie/<slug>/).
`text`	Yes	The note (plain text, up to 4000 characters).
`reply_to`	No	The id of a note to answer.
`slide_id`	No	The id of a slide (stable, the "id" of the slide in the presentation). Its number (position) changes when slides are reordered.

Output Schema

TableJSON Schema

Name	Required	Description
`id`	Yes
`text`	Yes
`agent`	No	Name of the AI agent that wrote it, if any.
`author`	No
`resolved`	No
`slide_id`	No	null: a note on the whole presentation.
`created_at`	No	ISO 8601 date and time.
`slide_number`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 28, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "agent": {
+      "description": "Name of the AI agent that wrote it, if any.",
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "author": {
+      "type": "string"
+    },
+    "created_at": {
+      "description": "ISO 8601 date and time.",
+      "type": "string"
+    },
+    "id": {
+      "type": "integer"
+    },
+    "resolved": {
+      "type": "boolean"
+    },
+    "slide_id": {
+      "description": "null: a note on the whole presentation.",
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "slide_number": {
+      "type": [
+        "integer",
+        "null"
+      ]
+    },
+    "text": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "id",
+    "text"
+  ],
+  "type": "object"
+}

First observedSep 28, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already establish this is a non-destructive, non-open-world write (readOnlyHint=false, destructiveHint=false). The description adds genuinely new behavioral context the annotations do not carry: who can see the note ('the owner sees the note in the viewer') and the thread audience ('the owner and whoever started it'), plus the visibility gate implied by 'any presentation you can see'.

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 sentences, no padding, and the three calling modes are front-loaded before the visibility note. The stacked em-dash/quoted-parameter construction is slightly awkward to parse but costs almost nothing in length.

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

Completeness4/5

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

An output schema exists, so return values need not be described. All four parameters are accounted for and all three call modes explained; the only unaddressed items are edge cases such as replying to a nonexistent or inaccessible note, which are minor for this tool.

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 already 100%, so the baseline is 3. The description earns above baseline by explaining the optionality semantics the schema does not: providing slide_id scopes the note to a slide versus the whole presentation, and reply_to turns the call into a threaded answer.

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?

The description states a specific verb+resource ('leave a note on any presentation') and enumerates the three targeting modes: slide-level (slide_id), presentation-level, and thread reply (reply_to). That is enough for an agent to distinguish it from read-only siblings like list_comments or destructive ones like delete_comment, though no sibling is named outright.

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 gives clear selection context: use slide_id to comment on a specific slide, omit it to comment on the whole presentation, and use reply_to to answer an existing thread. It does not state exclusions (e.g. when to prefer resolve_comment or what access is required), so it stops short of the top band.

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?