Skip to main content
Glama

samples

Browse ready-made film and shot samples, preview one, then add its shots to your scene, fill picture spots, or save your own scene as a sample. Use list, open, add, needs, save.

Instructions

Ready-made samples in the current style: whole films and shot runs (on shelves like "Whole films", "Film openings", "Hooks"), shot recipes (groups like "Big scenes", "Instagram hook"), and samples the person saved. action list (read-only; shelf or search narrows it), open (plays one in the preview without adding it; returns its shots and the pictures it needs), close, add (puts its shots in: how add = after the shot, shot = in place of the shot, scene = over the whole scene; returns new shot ids and picture spots to fill), needs (empty picture spots; fill them with fill_spot), save (saves a scene's shots as the person's own sample). Adding is one undo step. For single ids (a camera, an action) use library; for whole saved projects use templates.

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": {
      "action": "<action>"
    },
    "name": "samples"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoA sample id (or exact name) from list.
howNoFor add: add = after the shot, shot = in place of the shot, scene = over the whole scene.
nameNoFor save: the sample's name.
shotNoShot index from 0 in that scene.
groupNoFor needs: the group returned by add.
sceneNoScene index from 0. With no shotId/scene, the shot on screen is used.
shelfNoFor list: only this shelf.
actionYesWhat to do (see the description).
searchNoFor list: words to look for.
shotIdNoThe shot's id (from get_project).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.1.2
    • addedInput schema / properties / action / description
      Added value: +"What to do (see the description)."
    • addedInput schema / properties / how / description
      Added value: +"For add: add = after the shot, shot = in place of the shot, scene = over the whole scene."
    • changedInput schema / properties / name / description
      Previous value: -"For save."New value: +"For save: the sample's name."
    • addedInput schema / properties / search / description
      Added value: +"For list: words to look for."
    • addedInput schema / properties / shelf / description
      Added value: +"For list: only this shelf."
  2. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false and destructiveHint=false, and the description usefully adds that 'open' plays in the preview without adding anything and that 'adding is one undo step' — directly addressing the mutation/reversibility question the annotations leave open. It also discloses return payloads (shots, needed pictures, new shot ids, picture spots to fill). Idempotency and failure behaviour are not covered, keeping it at 4 rather than 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

The content is front-loaded with the resource definition, which is good, but the action list is delivered as a single dense run-on sentence with stacked parentheticals, making it harder to scan than a bulleted action breakdown. Every clause carries information, but the formatting works against quick parsing of six distinct actions.

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 10 parameters, six actions and no output schema, the description does the heavy lifting well: it explains what each action does, which parameters gate which action, and what each call returns (shots, needed pictures, new shot ids, spot counts). It does not document error or edge behaviour (invalid id, missing scene), but overall it is sufficient to invoke the tool correctly.

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?

Schema description coverage is 100%, so the baseline is 3. The description largely mirrors schema enum text (add = after the shot, shot = in place of the shot, scene = over the whole scene) and repeats 'id from list'. It adds some linkage value by tying shelf/search to list and group to needs, but nothing the schema does not already convey about type or format.

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?

The opening sentence concretely defines the resource (ready-made samples: whole films, shot recipes on named shelves, and person-saved samples) rather than restating the name 'samples'. It then enumerates the six actions with specific verbs, and explicitly carves out two neighbours ('for single ids ... use library; for whole saved projects use templates'). It stops short of a single crisp one-line summary, but an agent can identify the tool's domain and scope 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?

The closing sentence gives explicit routing rules to two siblings (library for single ids, templates for whole projects), and the parenthetical 'shelf or search narrows it' explains how to constrain list. Each action is briefly qualified (open 'without adding it', needs -> fill with fill_spot). It lacks negative guidance such as when not to add or what happens if an id is stale, so it falls just short of a 5.

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