Skip to main content
Glama
blackopsrepl

seshat

by blackopsrepl
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

recording_start

Start capturing an active display or region as a silent MP4, WebM, or GIF take; then stop and poll status to finalize the video.

Instructions

Start recording an active output (or a region within it) into a silent artifact: H.264 MP4 by default, or AV1 WebM, or a constrained GIF fallback. Returns immediately; call recording_stop to finish, then poll recording_status until the phase is completed or failed. The pointer cursor is always included. Narration anchors come from the timeline streams ingested for this take, so the tool server that drives the demonstration has to publish one.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
audioNoDesktop audio to capture alongside the picture. Defaults to off: the artifact stays silent unless you ask for a track. "monitor" records the desktop's default output (application and system sound); "mic" records the host's default microphone input; "auto" is monitor when a default sink is resolvable and mic otherwise. Ignored for gif (GIF cannot carry audio). Capturing with a narration added later puts speech on top of this track.off
formatNomp4: silent H.264 MP4 at 30 fps (default, widest compatibility); webm: silent AV1 WebM at 30 fps; gif: constrained fallback at 12 fps, 960 px maximum width.mp4
outputNoExact output name (Sway or Hyprland); inferred when exactly one output is active.
regionNoRegion fully contained in the selected output.
timeline_sourcesNoStream files to ingest for this take. Defaults to every *.jsonl file in streams/ under the seshat runtime directory. Paths are validated when the take starts.
max_duration_secondsNoAutomatic stop deadline. Defaults to 60 (mp4/webm) or 15 (gif); GIF recordings are capped at 15 seconds.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.4
    • addedInput schema / properties / audio
      Added value: +{
+  "default": "off",
+  "description": "Desktop audio to capture alongside the picture. Defaults to off: the artifact stays silent unless you ask for a track. \"monitor\" records the desktop's default output (application and system sound); \"mic\" records the host's default microphone input; \"auto\" is monitor when a default sink is resolvable and mic otherwise. Ignored for gif (GIF cannot carry audio). Capturing with a narration added later puts speech on top of this track.",
+  "enum": [
+    "auto",
+    "monitor",
+    "mic",
+    "off",
+    null
+  ],
+  "type": "string"
+}
    • changedInput schema / properties / output / description
      Previous value: -"Exact Sway output name; inferred when exactly one output is active."New value: +"Exact output name (Sway or Hyprland); inferred when exactly one output is active."
  2. First observedv0.1.1

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does so well: it discloses async behavior ('Returns immediately'), the default silent-artifact semantics, format/rate behavior, that the cursor is always captured, and a real prerequisite (the driving tool server must publish timeline streams for narration anchors). It omits permission/auth needs and failure modes, keeping it short of 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.

Conciseness4/5

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

Three sentences, front-loaded with the core action and default format, then workflow, then the prerequisite. Dense and mostly waste-free, though the 'pointer cursor is always included' note is a slight aside that could fold into the behavioral line.

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 6-param tool with no output schema and no annotations, the description covers the async start/stop/poll model, default artifact behavior, format and region options, and the timeline dependency. It stops short of return values or error conditions, but the lifecycle guidance largely compensates.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema: it frames the artifact as 'silent by default', ties timeline_sources to narration anchors, and restates the GIF constraint, clarifying intent for audio/format/timeline_sources rather than merely echoing enum values.

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 an active output (or a region within it)') and immediately scopes variants (MP4/WebM/GIF). It names and routes to the sibling lifecycle tools (recording_stop, recording_status), so an agent can distinguish it from recording_scenes or recording_voiceover 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?

Gives clear sequencing: call this, then recording_stop to finish, then poll recording_status until completed or failed. That is strong lifecycle context, but it does not state when NOT to use it or how it relates to peers like recording_scenes/recording_voiceover beyond the stop/status pair.

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