Skip to main content
Glama
Sign In

Cactal

by ai.cactal
OverviewDiscussionsAdmin

List changed source files

websiteSourceCode_changes_list
Read-onlyIdempotent

Lists added, removed, and modified file identities between two version refs, defaulting from published to head. Results use cursor pagination; pin continuation requests to the resolved version numbers.

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": {
      "websiteId": "<websiteId>"
    },
    "name": "websiteSourceCode_changes_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
toNoTarget side of the diff: a version number, `head`, or `published`. Defaults to `head`.
fromNoBase side of the diff: a version number, `head`, or `published`. Defaults to `published`.
limitNoMaximum candidate files to compare. Defaults to 20 and cannot exceed 20.
cursorNoOpaque cursor from the previous page. Continue with the returned resolved versions to keep the comparison pinned.
websiteIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive), so the description's value is the pagination behavior it adds: results are cursor-paginated and continuation requests must be pinned to the resolved version numbers rather than symbolic refs. That is genuinely non-obvious operating context. It stops short of saying what a result entry contains or how the resolved versions come back.

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?

Two sentences, no filler, with the core behavior front-loaded and the pagination caveat second. Every clause carries information the agent needs.

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 five-parameter read tool with no output schema, the description covers purpose, default scope, and the pagination discipline needed to page correctly. What is missing is a hint about the shape of returned entries (e.g., path plus change type), which matters slightly more because no output schema exists.

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 coverage is 80%; from, to, limit, and cursor are each documented, including the published/head defaults. The description restates the default window and the cursor pinning rule, largely duplicating the schema, and adds nothing about websiteId. Baseline 3 is appropriate.

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?

States a specific verb and resource: lists added/removed/modified file identities between two version refs. The word 'identities' implicitly separates it from the sibling websiteSourceCode_files_diff (contents), but that distinction is never made explicit, so an agent must infer the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives the default comparison window (published to head), which tells the agent the typical call shape, but never states when to prefer this over files_diff, files_list, or summary_get. Usage is implied rather than directed.

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

All Cactal toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources