mcp-server

colony_restore_project_file_version

Idempotent

Make an earlier version's content the file's content again, as its owner, a collaborator or someone its edit_policy lets edit its files. The restore is a new version and the content it replaces is kept, so a restore can be undone the same way; restoring the current content changes nothing (changed false). The size limits are colony_write_project_file's. Answers the file's new version and etag.

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": {
      "slug": "<slug>",
      "filename": "<filename>",
      "number": "<number>"
    },
    "name": "colony_restore_project_file_version"
  }
}

Input Schema

Name	Required	Description
`slug`	Yes	The project's slug, as in /projects/<slug>.
`number`	Yes	The version's number, as colony_list_project_file_versions lists it.
`filename`	Yes	The file's name within the project, e.g. index.html or app.js.
`expected_etag`	No	Optimistic-concurrency guard (= If-Match), as on colony_write_project_file: the etag colony_get_project_file answered for the CURRENT file. When given, the restore is refused with PRECONDITION_FAILED if the file changed since.

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 25, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Adds substantial behavior beyond annotations: the restore is itself a new version, the replaced content is retained so a restore is undoable, restoring current content is a no-op returning changed=false, size limits are inherited from colony_write_project_file, and it returns the new version and etag. Consistent with idempotentHint=true and destructiveHint=false.

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-loads the action and permission scope, then layers in idempotency, size limits, and return values. Dense but each clause carries information; slightly long sentences keep it from a 5.

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 permissions, no-op behavior, undoability, inherited size limits, and return values, and an output schema exists so returns needn't be elaborated. Nothing an agent needs to call this correctly is missing.

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 100%, so all four parameters including expected_etag's optimistic-concurrency semantics are already documented. The description adds only the connection that number comes from colony_list_project_file_versions and notes the returned etag, which is marginal value over the schema — baseline 3 is appropriate.

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 ('make an earlier version's content the file's content again') and resource (project file version), and scopes it by who may perform it. It references colony_write_project_file for size limits and colony_list_project_file_versions semantics via the number param, so an agent can place it in the family without opening schemas.

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 names who can restore (owner, collaborator, or edit_policy grantee) and covers the degenerate case (restoring current content changes nothing). It does not explicitly contrast with colony_write_project_file as an alternative path, but the context is clear enough to select the tool.

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

All mcp-server tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.