Skip to main content
Glama

glass_record

Records named workflows or buffers recent GUI session history for later export of marked evidence clips; requires a configured record directory.

Instructions

Record named workflows or explicitly buffer recent history; requires server --record-dir. Scoped start(name,max_duration_ms) acknowledges video; stop(outcome,keep) finalizes. Failures/cancellations keep by default; successes need keep:true. Buffer_start(history_ms) keeps 1–30s encoded history in memory (default 10s); check status.buffer_supported. Mark(name,outcome,keep,tail_ms) selects history plus a 0–5s tail (default 2s); overlapping marks merge into one pending clip. Save waits for the tail, exports the mark, and keeps buffering. Buffer_stop saves marked evidence by default; keep:false discards it. Unmarked history is always discarded. Scoped capture and buffering are exclusive. Clips are bounded to 60s/8MiB. Status reports scope, actual history and pending disposition. Read kept untrusted video through artifact URI resources/read. Never repeat UI input because recording failed.

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": {
      "op": "<op>"
    },
    "name": "glass_record"
  }
}

Input Schema

NameRequiredDescriptionDefault
opYes
keepNo
nameNo
outcomeNo
tail_msNo
history_msNo
max_duration_msNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.10.0

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations, the description discloses defaults, exclusivity, clip bounds, save/discard behavior, status reporting, artifact access via resources/read, and a failure caution. For a mutation-capable recording tool with minimal annotations, this is unusually rich behavioral context.

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?

The description is dense and front-loads the purpose and prerequisite before operation details. Every clause carries operational meaning, though the packed semicolon style makes some sections harder to scan than a lightly structured list would.

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?

For a seven-operation tool with no output schema, the description covers all operations, defaults, exclusivity, limits, and status reporting. It also explains how to read kept video through artifact URI resources/read, which is critical for completing the workflow.

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?

Schema coverage is 0%, so the description must carry parameter meaning and it does: it maps each op to its relevant parameters, explains keep semantics, and gives ranges and defaults for history_ms and tail_ms. It also covers name, max_duration_ms, outcome, and tail behavior.

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 states a specific verb and resource: record named workflows or explicitly buffer recent history. It distinguishes scoped capture from buffering and names the prerequisite server --record-dir, so an agent can identify the tool's role 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?

It gives clear operational guidance: use scoped start/stop for named workflows, use buffer_start/mark/save/buffer_stop for recent history, check status.buffer_supported, and note that scoped capture and buffering are exclusive. It lacks explicit sibling alternatives for cases like screenshots, but the internal mode selection is strong.

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