Skip to main content
Glama

import_project_zip

Create a new Overleaf project from a local .zip archive of LaTeX sources; the archive filename becomes the default project name.

Instructions

Create a new project from a local .zip archive of LaTeX sources. name defaults to the archive file name. The returned name is the one Overleaf stored, which can differ: Overleaf uses the root document's \title when present and adds " (n)" when the name is already taken; use it as confirmName. If the project was imported but its name could not be read back, the error (AUTH_EXPIRED, POLICY_DENIED, or TIMEOUT from that read, else REMOTE_ERROR) is never retryable and carries the new projectId in details; do not import again. Overleaf caps archives at about 50 MB and rate-limits this route: RATE_LIMITED means wait details.retryAfterMs before trying again, and nothing was created. Set the root document afterwards with update_project_settings if the archive has more than one .tex file at the top level.

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": {
      "localZipPath": "<localZipPath>"
    },
    "name": "import_project_zip"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoProject name, 1 to 150 characters without slashes
localZipPathYesLocal path of a .zip archive

Output Schema

NameRequiredDescriptionDefault
urlYes
nameYes
projectIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A4.3/5.0
Behavior4/5

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

Goes well beyond the idempotentHint=false/destructiveHint=false annotations: it discloses the ~50 MB cap, rate limiting with details.retryAfterMs, the guarantee that nothing was created on RATE_LIMITED, and the non-retryable post-import read failure that carries the new projectId. A small gap remains in not describing what the successful response body contains, though an output schema exists.

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 core action and the naming caveat before the error taxonomy, and every clause carries operational value. It is dense and the long conditional sentence about AUTH_EXPIRED/POLICY_DENIED/TIMEOUT takes effort to parse, but no sentence is 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?

Covers naming, size limits, rate limits, the dangerous non-retryable post-import case, and the follow-up settings call, so an agent can act correctly without guessing. With an output schema present, the return shape needn't be spelled out, leaving only minor gaps.

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 100%, so the baseline is 3, and the description earns a bump by explaining that name defaults to the archive file name, that Overleaf may override it from the root document's \title and append ' (n)', and that the returned name must be used as confirmName.

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 and resource ('Create a new project') and scopes it to 'a local .zip archive of LaTeX sources', which cleanly separates it from clone_project, create_project, and download_project_zip without needing to name them.

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?

Gives concrete follow-up routing ('Set the root document afterwards with update_project_settings if the archive has more than one .tex file at the top level') and a hard 'do not import again' rule after a post-import read failure. It does not explicitly state when to prefer create_project or clone_project instead, which keeps it from a 5.

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