Skip to main content
Glama
Sign In

Lazybird

by io.github.lazybirdai
OverviewDiscussionsAdmin

Export a project

export_project

Render a project to a file the user can download: video (mp4, mov), audio (mp3, ogg, wav) or the transcript (txt, docx, srt, vtt). Every block needs its speech first (generate_project_speech), and a video needs a picture. Renders in the background: get_exports shows when the file is ready. Each account renders a few exports at a time and a limited length of output a day.

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>",
      "type": "<type>",
      "format": "<format>"
    },
    "name": "export_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeYes
widthNovideo: the frame's width, even; the canvas's by default
formatYes
heightNovideo: the frame's height, even; the canvas's by default
projectIdYesA project id from list_projects or create_project
allowMissingSpeechNoExport even though some blocks have no speech; they're silent

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only say this is a non-read-only, non-destructive, non-idempotent, closed-world operation; the description adds genuinely new behavior — rendering is asynchronous in the background, completion is checked via get_exports, and there are per-account concurrency and daily output-length quotas. It stops short of clarifying what a repeat export of the same project produces (relevant to idempotentHint=false) or what happens on render failure.

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?

Four sentences, front-loaded with the purpose, then prerequisites, then async behavior, then limits. No redundant restatement of the title and no filler; each sentence contributes a distinct fact.

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 a six-parameter tool with no output schema, the description covers prerequisites, async completion path, quotas, and output formats — enough to invoke it correctly. Minor omissions are overwrite/duplicate behavior on re-export and how the finished file is retrieved beyond a bare pointer to get_exports.

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 coverage is 67%, so the schema already carries most parameter meaning. The description reinforces the type/format pairing and the speech prerequisite, but never mentions width/height framing or the allowMissingSpeech escape hatch, which are the parameters most likely to be misused. It adds some meaning but does not compensate for the uncovered third.

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?

The description opens with a specific verb and resource ("Render a project to a file the user can download") and immediately enumerates the three output types with their concrete formats (mp4/mov, mp3/ogg/wav, txt/docx/srt/vtt). An agent can distinguish this from generate_project_speech or get_exports without opening any schema.

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 states the preconditions explicitly: every block needs speech via generate_project_speech first, and video additionally requires a picture. It also names get_exports as the way to poll for completion. The only gap is that there is no explicit "do not use this when…" exclusion, so usage is strongly guided but not fully bounded.

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

All Lazybird 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