Skip to main content
Glama

manage_project

Destructive

Rename, trash, restore, archive, unarchive, or permanently delete Overleaf projects; require exact project name confirmation for trash, archive, and delete to prevent accidental changes.

Instructions

Rename, trash, restore, archive, unarchive, or permanently delete a project. trash, archive, and delete require confirmName to equal the current project name exactly, else CONFIRMATION_MISMATCH and nothing changes. trash is the normal way to remove a project and is reversible with restore or in the web UI. delete is permanent and only succeeds on a project that is already trashed. Confirm with the user before trashing or deleting.

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": {
      "projectId": "<projectId>",
      "action": "<action>"
    },
    "name": "manage_project"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionYes
newNameNoNew name, for rename
projectIdYesOverleaf project ID
confirmNameNoCurrent project name, repeated exactly, for trash, archive, and delete

Output Schema

NameRequiredDescriptionDefault
nameYes
actionYes
projectIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only flag destructiveHint=true and idempotentHint=false; the description adds the concrete guard that confirmName must equal the current name exactly, names the CONFIRMATION_MISMATCH failure and its all-or-nothing semantics ('nothing changes'), and explains reversibility of trash versus permanence of delete with its precondition. That is substantive behavioral context an agent cannot infer from the annotations.

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?

Four tight sentences ordered by importance: capability list, confirmation guard, trash semantics, delete semantics. No filler, and the safety-critical constraint appears immediately after the operation list rather than buried.

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?

An output schema exists, so return-value explanation is unnecessary, and the input schema covers the parameters. What remains — reversibility, preconditions, confirmation requirement, and failure signal — is fully addressed, making the definition complete for a destructive multi-action tool.

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 75% and already documents newName, projectId, and confirmName, so the baseline is 3. The description adds meaning beyond the schema by tying confirmName to a specific error code and no-op outcome, and by making the current-name match requirement exact, though it does not elaborate on projectId format or newName validation beyond the schema's length bounds.

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 first sentence names a specific resource (project) and enumerates the exact operations (rename, trash, restore, archive, unarchive, delete), which an agent can map directly onto the action enum. It also distinguishes mutation of an existing project from siblings like create_project or clone_project by framing these as lifecycle operations on a project that already exists.

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?

The description explicitly routes between the two removal paths: trash is 'the normal way to remove a project' and is reversible, while delete is permanent and only succeeds on an already-trashed project. It also states a prerequisite for user interaction (confirm before trashing or deleting) and names the web UI as an alternative recovery path.

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