Skip to main content
Glama

Padlet

by com.padlet
OverviewDiscussionsAdmin

Complete Attachment Upload

complete_attachment_upload
DestructiveIdempotent

Finish an upload started by start_attachment_upload. Call this once per local file, after the PUT to upload_url has succeeded. A chat-dropped file is downloaded by start_attachment_upload when you pass its file object, so do not call this tool for it.

This is what checks the file: its real size against the padlet's per-file limit, and its actual bytes against the content type declared at the start. A file that fails either check is deleted and cannot be attached.

Pass the same wall_url you passed to start_attachment_upload — the per-file limit belongs to the padlet, so completing against a different one can reject a file that was fine.

On success, pass the returned url to a post's attachment in create_posts or update_posts, the attachment of add_comment_to_post, or image_url of update_padlet_wallpaper or update_padlet_icon. One attachment per post or comment; call this once per file and use each URL once.

Returns { success: true, url: "...", file_name: "...", content_type: "...", size_bytes: 123 }, or { success: false, error_code: "...", message: "..." }.

Input Schema

NameRequiredDescriptionDefault
wall_urlYesThe padlet's link (e.g. https://padlet.com/foo/bar-a1b2c3): the link you were given, the `wall_url` a previous call returned, or a link the user pasted. Not a breakout-room or submission link, and not a padlet id: no tool takes a wall_id.
uploaded_urlYesThe `uploaded_url` start_attachment_upload returned. Not the upload_url you PUT the bytes to.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / wall_url / description
      Previous value: -"The padlet's link (e.g. https://padlet.com/foo/bar-a1b2c3): the link you were given, the `wall_url` a previous call returned, or a link the user pasted. Not a breakout-room or submission link."New value: +"The padlet's link (e.g. https://padlet.com/foo/bar-a1b2c3): the link you were given, the `wall_url` a previous call returned, or a link the user pasted. Not a breakout-room or submission link, and not a padlet id: no tool takes a wall_id."
  2. Changed3 schema fields changed
    • removedInput schema / properties / wall_id
      Removed value: -{
-  "description": "The id of the padlet the file will be attached to. Must be the same padlet you passed to start_attachment_upload.",
-  "type": "integer"
-}
    • addedInput schema / properties / wall_url
      Added value: +{
+  "description": "The padlet's link (e.g. https://padlet.com/foo/bar-a1b2c3): the link you were given, the `wall_url` a previous call returned, or a link the user pasted. Not a breakout-room or submission link.",
+  "maxLength": 2048,
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "wall_id",
-  "uploaded_url"
-]New value: +[
+  "wall_url",
+  "uploaded_url"
+]
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and idempotentHint=true, but the description adds the concrete consequence: size and content-type are verified, and a failing file is deleted and cannot be attached. It also warns that completing against a different wall_url can reject a valid file, which is behavior no annotation expresses.

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?

Front-loaded with the purpose and the call-ordering rule, and the failure semantics follow. It is on the long side for two parameters, with some downstream-integration detail that could be trimmed, but nothing is genuinely wasted.

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?

No output schema exists, yet the description spells out both success and error return shapes, the validation performed, and the downstream consumers of the URL. An agent has everything needed to call it and use the result.

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%, so the baseline is 3. The description goes further by explaining why the same wall_url must be reused (the per-file limit belongs to the padlet) and that uploaded_url comes from start_attachment_upload, not the upload_url you PUT to.

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 ('Finish an upload started by start_attachment_upload'), and explicitly excludes the sibling-driven case where start_attachment_upload already downloaded a chat-dropped file. An agent can place this tool in the two-step upload flow without opening 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 Guidelines5/5

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

Very explicit: call once per local file, only after the PUT to upload_url succeeded, never for chat-dropped files. It also says exactly where the returned url goes (create_posts/update_posts attachment, add_comment_to_post, update_padlet_wallpaper/update_padlet_icon) and that each URL is single-use.

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

All Padlet 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