Skip to main content
Glama

get_project_tree

Read-only

Retrieve a project's file and folder tree with entity IDs and paths, plus root document, compiler, TeX Live image, spell-check language, and optional dashboard tags for review or editing.

Instructions

Return the project file/folder tree with entity IDs and paths, plus the root document, compiler, TeX Live image, and spell-check language Overleaf uses. Each binary file entity carries hash, a git blob hash equal to git hash-object <file>; text documents have no hash and must be compared by reading their content. includeTags adds tags, this account's dashboard tags on the project as { id, name }, from one more request; change them with manage_tags.

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>"
    },
    "name": "get_project_tree"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectIdYesOverleaf project ID
includeTagsNoAdd this account's tags on the project; one more request to Overleaf

Output Schema

NameRequiredDescriptionDefault
tagsNo
compilerNo
entitiesYes
hashNoteYes
imageNameNo
rootDocPathNo
spellCheckLanguageNo
trackChangesActiveYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already establish readOnlyHint=true, and the description adds genuinely new behavior: binary entities carry a git blob hash equivalent to `git hash-object <file>`, while text documents have no hash and must be compared by reading content. It also discloses that includeTags triggers an additional request. Remaining gaps (pagination, tree size limits, error behavior) are modest given the 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-loaded with the main return value and the hash/text distinction before the tag clause, with no filler sentences. The final sentence runs long and packs three separate ideas (tag shape, request cost, mutation alternative) into one clause chain.

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?

With an output schema present, the description need not enumerate return fields, yet it still explains the semantically tricky part (hash presence/absence) that an agent could misread. It is nearly complete for a two-parameter read tool; only pagination and large-project behavior are unaddressed.

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%, and the schema already documents includeTags' purpose and its extra-request cost, so the baseline is 3. The description adds only the returned tag shape ({ id, name }) and the manage_tags pointer; projectId gets no additional semantics beyond the schema's 'Overleaf project ID'.

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 ('Return the project file/folder tree') and enumerates what the response carries: entity IDs and paths, root document, compiler, TeX Live image, and spell-check language. An agent can distinguish this metadata/tree snapshot from document-reading siblings like get_full_document or read_file without opening any schema.

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 explicitly routes tag mutation away from this tool to manage_tags, and flags the cost condition for includeTags ('from one more request'). It does not, however, state when to prefer this over get_sections or read_file for inspecting content, so the scope boundary is only partially drawn.

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