Skip to main content
Glama
Custodia-Admin

Pagebolt

by Custodia-Admin
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

export_sequence

Turn a list of steps into a PageBolt sequence you (or the user) can edit and re-run: returns JSON to paste into the dashboard Sequence Builder ("Import JSON" - the same place "Edit sequence" opens), and it can optionally save it to the…

Instructions

Turn a list of steps into a PageBolt sequence you (or the user) can edit and re-run: returns JSON to paste into the dashboard Sequence Builder ("Import JSON" - the same place "Edit sequence" opens), and it can optionally save it to the user's Saved Automations (save:true). Use it after you have planned a video/sequence so the user can tweak steps, highlights and narration themselves, or re-run it later with record_video / run_sequence. Does not run the sequence or consume quota. Put {{username}}/{{password}} placeholders in fill steps instead of real credentials; never include cookies.

Input Schema

NameRequiredDescriptionDefault
nameYesName for the sequence (used when saved).
paceNoVideo pace multiplier (video only).
saveNoIf true, also save it to the user's Saved Automations (appears in the dashboard and extension Library). Default false.
typeNo"video" if it will be recorded with record_video (default), "sequence" for run_sequence.
stepsYesSteps, same shape as record_video / run_sequence steps: {action, url|selector|value|key|ms|x|y|script|style|color|duration|note|narration|pauseAfter|optional}. Prefer scrolling by selector, never guessed pixel offsets.
formatNoVideo format (video only).
viewportNoViewport size.
audioGuideNoNarration settings (video only).
descriptionNoOptional description.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.17.1
    • addedInput schema / properties / audioGuide / properties / elevenlabs
      Added value: +{
+  "additionalProperties": false,
+  "description": "ElevenLabs voice settings (no key: it is never saved).",
+  "properties": {
+    "modelId": {
+      "type": "string"
+    },
+    "similarityBoost": {
+      "maximum": 1,
+      "minimum": 0,
+      "type": "number"
+    },
+    "speakerBoost": {
+      "type": "boolean"
+    },
+    "stability": {
+      "maximum": 1,
+      "minimum": 0,
+      "type": "number"
+    },
+    "style": {
+      "maximum": 1,
+      "minimum": 0,
+      "type": "number"
+    },
+    "voiceId": {
+      "type": "string"
+    },
+    "voiceName": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}
    • addedInput schema / properties / audioGuide / properties / provider
      Added value: +{
+  "description": "TTS provider. \"elevenlabs\" = the user's own ElevenLabs account; the key is NEVER saved: supply it at record time (ELEVENLABS_API_KEY).",
+  "enum": [
+    "azure",
+    "openai",
+    "elevenlabs"
+  ],
+  "type": "string"
+}
  2. Addedv1.17.0

TDQS

A4.5/5.0
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 well: it discloses the side effect of save:true (persists to Saved Automations/Library), that no execution or quota occurs, and a security constraint (use {{username}}/{{password}} placeholders, never cookies). It omits auth/permission requirements and any size or rate limits on the returned JSON.

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?

Front-loaded with the core action and return value, and every sentence carries information (output destination, optional save, when to use, no-quota guarantee, security rule). It is dense with parentheticals and could be split for readability, but nothing is filler.

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 9-parameter tool with nested objects, no annotations and no output schema, the description covers the critical gaps: it says what is produced (importable JSON), that saving is optional, and that nothing runs. It stops short of describing the returned JSON's shape, which matters given there is no output schema.

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 explains what save:true actually does in user-visible terms and adds the credential-placeholder rule for fill steps, which the schema does not state. It does not, however, clarify the type/pace/audioGuide interplay for video vs sequence.

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+resource ('Turn a list of steps into a PageBolt sequence') and immediately clarifies the output form (JSON for the dashboard Sequence Builder / Import JSON). It explicitly distinguishes itself from record_video and run_sequence by stating it does not run the sequence.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Gives explicit when-to-use ('after you have planned a video/sequence so the user can tweak steps... or re-run it later'), names the alternatives (record_video / run_sequence), and states a when-not ('Does not run the sequence or consume quota'). Nothing is left to inference.

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