Skip to main content
Glama
SoManyLemons MCP

SoManyLemons MCP

Official
by NoMiddleInc

Start browser recording

start_browser_recording
Read-onlyIdempotent

Open a browser-based camera or microphone recording session and receive a recorder page URL plus a start timestamp for identifying new recordings. No recording starts until the user records.

Instructions

Opens a new camera or microphone recording session in the browser: returns record_url, the ProducerSpark recorder page for the user to open, and started_at, which identifies recordings made after it. Nothing is recorded or changed by this call.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "start_browser_recording"
  }
}

Input Schema

NameRequiredDescriptionDefault
account_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.36

TDQS

A4/5.0
Behavior4/5

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

The description meaningfully supplements the annotations by pre-empting the misleading 'start recording' name ('Nothing is recorded or changed by this call') and by naming the two return fields, including the semantics of started_at as a marker for later recordings. It does not address session lifetime or whether repeated calls yield distinct sessions, which is a notable gap given idempotentHint=true on a call that 'opens a new' session.

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?

Two tight sentences, front-loaded with the action and its outputs, with the safety clarification last. Nothing is padding; each clause adds 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 zero-required-parameter, non-mutating tool with no output schema, the description covers what is returned and that nothing is persisted, which is most of what an agent needs. It stops short of describing the follow-on path (user opens the URL, then recording artifacts are retrieved later), so it is strong but not fully closed.

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?

The sole parameter (account_id, optional) is not mentioned anywhere in the description, so the description adds no meaning beyond the structured schema. Counterbalancing this, the input schema itself carries a fairly complete usage note for account_id ('Only for a teammate who was added to more than one account'), so the practical loss is limited.

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 ('Opens a new camera or microphone recording session in the browser') and immediately describes what the call yields (record_url, started_at), which lets an agent distinguish it from the upload/recording siblings such as create_recording_upload or add_recording without opening their schemas.

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?

Usage is implied by 'in the browser' and 'the ProducerSpark recorder page for the user to open', which sketches the browser-capture flow, but there is no explicit when-to-use versus an alternative (e.g. upload-based recording) and no stated prerequisites, so an agent must infer selection.

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

Deploy Server

Other Tools