Skip to main content
Glama
aseprite-claude-connector

aseprite-claude-connector

set_safety_rails

Idempotent

Configure session safety limits: enable dry-run to preview edits as rolled-back errors, and cap pixel changes per call so oversized edits roll back automatically.

Instructions

Set the safety rails for this session, or pass nothing to read them. dry_run true makes every edit report what it would change, as an error, then roll back; tools that save, export, or run raw Lua refuse instead. max_changed_pixels caps what one call can change, and an edit over it is rolled back; 0 removes the cap. It counts hidden layers. move_layer isn't capped, and run_lua is capped only with edit=true.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "set_safety_rails"
  }
}

Input Schema

NameRequiredDescriptionDefault
dry_runNo
max_changed_pixelsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4.5/5.0
Behavior5/5

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

With only idempotentHint available, the description carries the full burden and does so in detail: dry_run causes edits to report their intended changes as errors and then roll back, save/export/raw-Lua tools refuse instead, and cap violations roll back. It also discloses non-obvious scope rules: hidden layers count, move_layer is exempt, and run_lua is capped only with edit=true.

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?

The description is front-loaded with the action and read alternative, then explains each parameter in a tight sentence. The backtick-delimited parameter names keep it scannable, though the embedded clauses about move_layer and run_lua make it denser than strictly necessary.

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?

There is no output schema, yet reading the rails is described as 'read them', which leaves the return shape vague. Everything an agent needs in order to call the tool correctly, including exemptions and the 0 semantic, is present.

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 description coverage is 0%, so the description must supply all meaning, and it does: dry_run's rollback-and-error mode and max_changed_pixels' per-call cap, hidden-layer counting, and 0-means-unlimited convention. The only gap is that null (the schema default) is not explicitly tied to the read behavior, though 'pass nothing to read them' implies it.

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?

The description opens with a specific verb and resource: 'Set the safety rails for this session, or pass nothing to read them.' It also discloses a dual behavior: writing when values are supplied and reading when nothing is supplied. No sibling tool name resembles this one, so an agent can identify it unambiguously.

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?

It explicitly states when to pass nothing (to read the current rails) and defines the effects of both settings, so the agent knows how each parameter governs subsequent edits. The guidance is slightly implicit about precedence, such as what happens if both dry_run and max_changed_pixels are set, and it does not discuss resetting the rails to their defaults.

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