Skip to main content
Glama

Valmera — agentic AI video editor

by io.valmera
OverviewDiscussionsAdmin

Suggest motion beats

suggest_motion_beats

PROJECT-SCOPED: this call acts only on the explicit project_id and returns the project identity with its result. READ: a timed premium beat sheet of GRAPHICS for the CURRENT program: hook interrupt at 0 s, counters on spoken numbers (values parsed from the words), checklists on enumerations, versus cards on contrasts, hero word slams on emphasis words, native-UI CTAs on spoken calls to action — each with program times, template, extracted params and the transcript to paraphrase — plus long holds as a diagnostic. Zooms and sound effects are optional, never rules, so both are OFF by default: camera=true adds a short list of moments that could earn a camera move (never one per cut or hold), sounds=true names the approved library sound each beat could take. Call it after the cut and captions are set, then place the beats you agree with.

Input Schema

NameRequiredDescriptionDefault
cameraNoopt in to a few optional camera candidates (default false)
soundsNoopt in to optional library-sound suggestions per beat (default false)
densityNospacing between hero beats (premium ≈ every 2-3 s)
project_idYesRequired immutable scope for this call. Copy the id from list_projects/open_project/project_state; the active-project pointer is never used to guess.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / camera
      Added value: +{
+  "description": "opt in to a few optional camera candidates (default false)",
+  "type": "boolean"
+}
    • addedInput schema / properties / sounds
      Added value: +{
+  "description": "opt in to optional library-sound suggestions per beat (default false)",
+  "type": "boolean"
+}
  2. Added

TDQS

A3.7/5.0
Behavior1/5

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

The description explicitly labels the call 'READ' and frames it as scoped/analysis-only, while the annotations declare readOnlyHint=false (and idempotentHint=false). This is a direct text-vs-structured conflict that could lead an agent to assume the call has no side effects when the server says otherwise. Flagged as an annotation contradiction.

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-loads the project scoping and read/usage constraints before the detail, and there is no filler sentence. The middle sentence is a very dense single-line enumeration of beat types that would scan better as a list, but every clause carries 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?

With no output schema, the description does the heavy lifting of describing the return: program times, template, extracted params, transcript to paraphrase, plus long holds as a diagnostic. Defaults for the optional flags are stated. The remaining gap is the unresolved read-only/side-effect question raised by the READ label versus readOnlyHint=false.

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 parameter documentation is already carried by the schema (baseline 3). The description still adds real meaning beyond it — camera=true yields 'a short list of moments that could earn a camera move (never one per cut or hold)' and sounds=true 'names the approved library sound each beat could take' — clarifying the semantics of the optional flags rather than repeating them.

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 — it returns a timed premium beat sheet of graphics for the current program — and enumerates exactly what a 'beat' is (hook interrupt, counters, checklists, versus cards, hero-word slams, native-UI CTAs). This clearly distinguishes it from placement siblings like add_motion_graphic/set_motion_graphic and from adjacent suggest_* tools.

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 an explicit prerequisite and workflow: 'Call it after the cut and captions are set, then place the beats you agree with' — making clear the tool only suggests and a separate call applies them. It does not, however, name or exclude overlapping siblings such as suggest_emphasis, so the routing guidance stops short of fully disambiguating alternatives.

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

All Valmera — agentic AI video editor toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources