Skip to main content
Glama

keys

Set, remove, or clear timed animation values on tracks to hand-animate characters, items, text, lights, scenes, masks, adjustments, and elements.

Instructions

Animate anything by hand with keyframes on a track. Tracks: "cast:" (x, y, z, size, spin, turn), "item:" (x, z, size), "text:" (x, y, size), "light:" (x, y, z, intensity, color), "scene:light" (level, ambient), "mask:shot", "adjust:", "element:". op set puts values at a time (a first key after 0 also keys the resting value at 0), remove deletes the key at that time, clear drops the track. One undo step for the person. For ready-made moves use act; for the camera use camera keys.

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": {
      "track": "<track>"
    },
    "name": "keys"
  }
}

Input Schema

NameRequiredDescriptionDefault
atNoSeconds into the shot.
opNoset if left out.
easeNoHow it travels on to the next key: smooth, even, fast-start, slow-start, punch, bounce.
shotNoThe shot's id (from get_project). Left out: the shot on screen.
trackYesWhich thing, like "cast:member-1" or "scene:light" (ids from get_shot).
valuesNoLike {"x": 3, "size": 1.4}.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.2
    • changedInput schema / properties / ease / description
      Previous value: -"smooth, even, fast-start, slow-start, punch, bounce"New value: +"How it travels on to the next key: smooth, even, fast-start, slow-start, punch, bounce."
    • addedInput schema / properties / op / description
      Added value: +"set if left out."
    • addedInput schema / properties / track / description
      Added value: +"Which thing, like \"cast:member-1\" or \"scene:light\" (ids from get_shot)."
  2. First observedv0.1.0

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, but the description adds useful context the annotations cannot: the hidden side effect that 'a first key after 0 also keys the resting value at 0', that clear 'drops the track', and the undo granularity ('One undo step for the person'). It stops short of saying whether a track must already exist or what the call returns, so it adds value but not a full behavioral picture.

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, then the track table, then op semantics, then sibling routing — a sensible information hierarchy. The track enumeration is long but each entry carries distinct payload information, so little is wasted; a few clauses overlap with schema text.

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 six-parameter, nested-object mutation tool with no output schema, the definition covers the track vocabulary, the three operations, undo scope, and sibling alternatives. The remaining gaps — whether tracks are auto-created, how existing keys can be inspected (no read op is offered), and expected response — are minor but real.

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 earns above baseline by expanding the track string grammar into concrete per-namespace property lists that the schema only hints at ('cast:member-1'). It also explains op semantics ('set puts values at a time', 'remove deletes the key at that time') beyond the bare 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 — 'Animate anything by hand with keyframes on a track' — then enumerates every track namespace (cast, item, text, light, scene:light, mask, adjust, element) with the properties each accepts. This is far more specific than the bare name 'keys' and lets an agent distinguish it from act and camera 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?

Explicitly routes the agent away from this tool for two cases: 'For ready-made moves use act; for the camera use camera keys.' That is real when-to-use-else guidance. It does not address the sibling tool named 'remove', even though this tool also exposes op=remove, leaving a genuine disambiguation gap.

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