Skip to main content
Glama
pedra-ai

Pedra MCP Server

Official
by pedra-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Edit existing video

pedra_update_video

Edit an existing video (by videoId) without re-rendering unchanged clips — only new/changed photos re-animate and cost credits; reordering, music, voice, branding and text re-stitch for free.

Instructions

Edit an existing video (by videoId) without re-rendering unchanged clips — only new/changed photos re-animate and cost credits; reordering, music, voice, branding and text re-stitch for free. Omit images to change only audio/text/branding while keeping the current timeline. Omit music/voice/branding/ending text to leave them unchanged. Blocks until rendered and returns the new video URL.

Input Schema

NameRequiredDescriptionDefault
musicNo
voiceNo
imagesNoFull ordered image list to rebuild the timeline; matching photo+effect clips are reused. Omit to edit only audio/text and keep the current timeline.
videoIdYesId of the video to edit (from pedra_create_video).
brandingNo
isVerticalNoForce a vertical (9:16) video (only when images are sent).
endingTitleNo
endingSubtitleNo
propertyCharacteristicsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.6.1
    • changedInput schema / properties / images / items / properties / effect / description
      Previous value: -"Animation for this image. Defaults to \"zoom-in\"."New value: +"Animation for this image. Defaults to \"zoom-in\" (AI, 5 credits). \"transition\" morphs between two photos; \"sky-transition\" changes only the sky and light between two versions of the same photo (day to night, day to sunset); both need secondImageUrl and cost 5 credits. \"lite-zoom-in\" / \"lite-zoom-out\" are a free, subtler 3D push (no AI video, 0 credits). \"static\" is a still frame, also free."
    • changedInput schema / properties / images / items / properties / effect / enum
      Previous value: -[
-  "zoom-in",
-  "zoom-out",
-  "transition",
-  "static"
-]New value: +[
+  "zoom-in",
+  "zoom-out",
+  "transition",
+  "sky-transition",
+  "lite-zoom-in",
+  "lite-zoom-out",
+  "static"
+]
    • changedInput schema / properties / images / items / properties / secondImageUrl / description
      Previous value: -"Required when effect is \"transition\"."New value: +"Required when effect is \"transition\" or \"sky-transition\"."
  2. Changed1 schema field changedv0.5.1
    • changedInput schema / properties / images / items / properties / imageUrl / description
      Previous value: -"Source image: a public https:// URL, a data: URI, or an absolute path to a local image file (the file is read and inlined automatically)."New value: +"Source image: a public https:// URL, a data: URI, or an absolute path to a local image file on this computer (the file is read and inlined automatically). If the photo is on the user's device and can't be read from here (e.g. it's on their phone), get a link from pedra_create_upload_link."
  3. Addedv0.3.0

TDQS

A4.1/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing the credit model (only new/changed photos cost credits; reordering, music, voice, branding and text re-stitch for free), the blocking-until-rendered behavior, and that it returns the new video URL. Annotations only cover the safety profile (readOnly=false, destructive=false, openWorld=true); the cost and latency traits are the substantive additions here.

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 dense sentences, front-loaded with the identity and cost model before the omit rules. Every clause carries decision-relevant information; nothing is repeated from the schema or annotations.

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?

No output schema exists, but the description compensates by stating it blocks until rendered and returns the new video URL. Cost behavior and partial-rebuild semantics are covered; the remaining gap is the unaddressed `propertyCharacteristics` and `isVertical` parameters for a 9-parameter nested tool.

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?

With only 33% schema description coverage across 9 parameters, the description must compensate, and it partially does — it explains the omit-to-leave-unchanged semantics for `images`, `music`, `voice`, `branding` and ending text. But `propertyCharacteristics` and `isVertical` (beyond a note in the schema) get no mention, and the 'keeps current timeline' interaction with the image effect reuse rule is only sketched.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource — 'Edit an existing video (by videoId)' — and immediately contrasts it with the creation path by noting only new/changed clips re-animate. It never names pedra_create_video or pedra_edit_via_prompt explicitly, so the sibling differentiation is implied by 'existing' rather than stated.

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 concrete selection semantics: omit `images` to keep the timeline and change only audio/text/branding, omit `music`/`voice`/`branding`/ending text to leave those untouched. That is clear when-to-use guidance, but it offers no exclusion rules or explicit comparison against pedra_create_video or pedra_edit_via_prompt.

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