Lazybird

Edit a project

edit_project

Change the project. Changes apply in order, all or none. update_project: its name, details, master volume, and whether speech is made after each edit. The voiceover: insert_voiceover adds a block of text or SSML, or a pause, after or before a voiceover item, else at the end; update_voiceover changes a block's text, voice, voice settings or pauses, or a pause's length; move_voiceover moves an item next to another on its voice track, the items between closing up; delete_voiceover removes one. The picture and sound, in the shapes read_video_guide gives: add_block, update_block and delete_block for elements, video, images and audio; add_animation, update_animation and delete_animation; set_canvas; set_style and delete_style; set_font and delete_font; set_variable and delete_variable. New items get ids of their own: give each a ref, and later changes in the same call can use the ref as its id. Blocks whose text, voice or settings change need speech again. Read read_video_guide before your first picture or sound change.

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": {
      "projectId": "<projectId>",
      "changes": "<changes>"
    },
    "name": "edit_project"
  }
}

Input Schema

Name	Required	Description	Default
`changes`	Yes
`projectId`	Yes	A project id from list_projects or create_project

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 9, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Adds substantial behavior beyond the annotations: all-or-none atomicity, in-order application, capped at 200 changes via schema, the ref-to-id aliasing that lets later changes in the same call reference a new item, and the speech-regeneration side effect. It never warns that delete_* removes content irreversibly, which sits in mild tension with destructiveHint=false, but the deletes are bounded project edits rather than data destruction.

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

Conciseness3/5

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

Roughly 180 words for 18 action types is not wasteful, but the prose is semicolon-fragmented and front-loading is weak: the second sentence begins mid-list with "update_project: its name, details..." before the agent has been told what the list represents. Information density is high, readability is low.

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?

For an 18-action, up-to-200-item batch mutation tool with no output schema, it covers ordering, atomicity, ref reuse, side effects, and defers element/video shapes to read_video_guide, which is enough to call it safely. It omits the return value and error semantics for a rejected batch, which would be the remaining gap.

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

Parameters5/5

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

The `changes` array itself carries no top-level schema description, and the description compensates by mapping each action name to the fields it consumes (id vs ref, after/before for placement, pause vs text/ssml) and by clarifying that placement options are alternatives. Schema property descriptions are rich, but the description supplies the action-to-parameter grammar that the schema alone leaves scattered.

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 opening "Change the project" plus the enumeration of change types (update_project, voiceover insert/update/move/delete, blocks, animations, canvas, styles, fonts, variables) makes it clear this is a batch mutation tool over a project, and it names read_project/generate_speech as related operations. It is not confused with any sibling, though the first two sentences are telegraphic and only become intelligible after reading the whole list.

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?

Gives an explicit prerequisite ("Read read_video_guide before your first picture or sound change") and a conditional rule that changed text/voice/settings require speech again, which tells the agent when to also call generate_speech. It does not state when NOT to use this tool or contrast it with a single-item alternative, so it stops short of full routing guidance.

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

All Lazybird 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.