Skip to main content
Glama

list_projects

Read-only

Retrieve accessible Overleaf projects, newest first, with filters for tags, names, archived, and trashed status, returning IDs, metadata, and totals to help you find and manage projects.

Instructions

List the projects the account can access, newest first by default. Archived and trashed projects are hidden unless includeArchived or includeTrashed is set. Returns projects with id, name, accessLevel, lastUpdated, archived, and trashed, plus totalMatched (before limit) and totalProjects (everything the account can access). includeTags adds each project's tags ({ id, name }) and tags, every tag of the account with its id, name, color, and projectCount, empty ones included; use these ids with manage_tags. tag lists only the projects in the tag with that exact name; an unknown name is NOT_FOUND. Tags are the dashboard's own labels for this account; collaborators do not see them.

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": "list_projects"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagNoExact name of a tag; only its projects are listed
sortNolastUpdated is newest first; name is alphabeticallastUpdated
limitNoMaximum projects returned, at most 200
queryNoCase-insensitive substring of the project name
includeTagsNoAdd each project's tags and the account's tags; one more request to Overleaf
includeTrashedNo
includeArchivedNo

Output Schema

NameRequiredDescriptionDefault
tagsNo
projectsYes
totalMatchedYes
totalProjectsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A4/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true, and the description goes well beyond that: default hiding of archived/trashed items, the fact that includeTags costs 'one more request to Overleaf', the NOT_FOUND error for an unknown tag name, and the visibility caveat that tags are dashboard-only and invisible to collaborators. Those are real behavioral facts an agent cannot get from the annotations. The only gap is pagination/limit interaction beyond the totalMatched note.

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 core behavior and defaults are front-loaded in the first two sentences, and every subsequent sentence carries distinct information about return fields, totals, or tag behavior. It is a dense single paragraph with some run-on clauses around includeTags, which costs a little readability but no filler.

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 7-parameter read tool with an output schema, the description covers the non-obvious parts: hidden-by-default states, the difference between totalMatched and totalProjects, the shape of tag data, and one error case. The presence of an output schema means return values need not be exhaustively described, so remaining omissions are minor.

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 71%, so the schema already documents most parameters; the description still adds meaning the schema lacks, notably what includeTags actually returns (each project's tags plus every account tag with projectCount, empty ones included) and that tag matches an exact name and yields NOT_FOUND otherwise. sort, query, and limit are left to the schema, which already covers them adequately.

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?

The description opens with a specific verb and resource plus scope: 'List the projects the account can access, newest first by default.' That is far more than a restatement of the name, and the account-level scope is stated explicitly. It does not explicitly contrast itself with search_project, so sibling differentiation is only partial (it does route to manage_tags for tag ids).

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 gives concrete conditions: archived and trashed projects are hidden unless includeArchived or includeTrashed is set, and tag narrows results to one exact tag name. It also names a follow-on tool ('use these ids with manage_tags'), which is genuine routing guidance. It stops short of saying when to prefer this over search_project or get_project_tree.

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