Skip to main content
Glama

edit_project

Edit any project setting by JSON Pointer path when specific tools don't cover the field; batch changes as one undo step, with invalid paths or values refused.

Instructions

Low-level edit of any project setting by JSON Pointer path (read how_to once for the format, get_shot for a real shot). Each change: {"op":"replace"|"add"|"remove"|"merge","path":"/scenes/0/shots/1/seconds","value":4}. All changes in one call are one undo step; a bad path or value is refused and nothing changes. Returns { done: number of changes }. Prefer the specific tools (cast, act, words, camera, light, place, transition, keys); use this only for fields they don't cover.

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": {
      "changes": "<changes>"
    },
    "name": "edit_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
labelNoWhat the person sees in the undo note, like 'Claude made shot 2 longer.'
changesYesThe changes, applied in order as one undo step.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.2
    • addedInput schema / properties / changes / description
      Added value: +"The changes, applied in order as one undo step."
    • addedInput schema / properties / changes / items / properties / op / description
      Added value: +"replace a value, add one (append to a list with path ending '-'), remove it, or merge fields into an object."
    • addedInput schema / properties / changes / items / properties / path / description
      Added value: +"JSON Pointer into the project, like \"/scenes/0/shots/1/seconds\"."
    • addedInput schema / properties / changes / items / properties / value / description
      Added value: +"The new value. Not needed for remove."
  2. First observedv0.1.0

TDQS

A4.7/5.0
Behavior4/5

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

Goes well past the annotations: it discloses atomicity ('all changes in one call are one undo step'), validation behavior ('a bad path or value is refused and nothing changes'), and the return shape ('Returns { done: number of changes }'). The one tension is that it documents a 'remove' op while destructiveHint=false, though the atomic undo step and all-or-nothing refusal make removals reversible, so this is disclosed rather than contradicted.

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, each doing distinct work: capability, mechanics/atomicity, and tool-selection guidance. The routing advice to specific tools comes last as an exclusion, but the core purpose is front-loaded and there is no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers everything needed to call a low-level mutation tool: path format source, change payload shape, atomicity and failure semantics, return value, and when to prefer alternatives. No output schema exists, yet the return shape is still stated, and the surrounding annotations fill in the safety profile.

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 baseline is 3, but the description adds a concrete change payload ({"op":"replace","path":"/scenes/0/shots/1/seconds","value":4}) that the schema only describes abstractly. It also points to how_to for the path vocabulary, which is the real semantic gap since the schema can't enumerate valid JSON Pointers.

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 ('Low-level edit of any project setting') plus the mechanism ('by JSON Pointer path'), and immediately names the sibling category it is not ('prefer the specific tools'). An agent can distinguish it from cast/act/camera/light etc. without opening any schema.

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?

Explicit when-not guidance: 'Prefer the specific tools (cast, act, words, camera, light, place, transition, keys); use this only for fields they don't cover.' It also routes the agent to how_to for the path format and get_shot for a concrete example, so prerequisites and alternatives are both covered.

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