Skip to main content
Glama

record_start

Start recording a session's screen flow so every key press becomes a reproducible step, excluding passwords. Stop recording later with record_stop.

Instructions

Start recording a screen flow on this session: every key pressed from now on (by you or by the user in the viewer) becomes a step. Passwords are never recorded. Finish with record_stop.

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": "record_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
sessionNosession name; lets you run several side by sidemain

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only declare this is a non-read-only, non-destructive operation; the description adds substantive behavior on top: keypresses from both the agent and the viewer become steps, and passwords are never captured. The privacy guarantee and the recording lifecycle are exactly the kind of context annotations cannot convey. It does not address re-entrancy or whether starting twice is an error, which keeps it from a 5.

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?

Three short sentences with the action, the recording scope, and the closing instruction in that order — front-loaded and free of filler. Nothing could be removed without losing information.

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 simple one-parameter state-toggle tool with an output schema and annotations present, the description covers purpose, scope, privacy behavior, and the follow-up call. The only omissions are edge-case behavior when a recording is already running and any mention of the session argument.

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 description coverage is 100% and the single session parameter is already documented as a name allowing parallel sessions. The description never mentions the session parameter, so it adds no meaning beyond the schema; baseline 3 applies.

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 ("Start recording a screen flow on this session") and immediately defines the scope of what becomes a step, which distinguishes it cleanly from record_stop and the other session tools. An agent can identify the operation 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 Guidelines4/5

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

The description establishes the starting condition ("from now on") and explicitly names the terminating counterpart, record_stop, so the agent knows this is one half of a paired lifecycle. It stops short of stating exclusions, such as what happens if a recording is already active on the session.

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