Skip to main content
Glama

plan_sync

Read-only

Previews synchronization between a local folder and an Overleaf project, reporting files to upload, identical items, remote-only paths, conflicts, and ignored entries without making changes.

Instructions

Compare a local folder with a project folder and report what sync_directory would do, changing nothing. Binary files compare by git blob hash at no cost; each text document with a local counterpart, or present only in the project, is read once through the project's queue, so this suits tens of documents, not thousands. Returns toUpload (new or changed), identical (a count and the first 25 paths unless verbose), remoteOnly (what mirror mode would delete, each folder collapsed to one entry that includes its contents), conflicts (a file where the other side has a folder, or non-UTF-8 text where the project has a document; sync_directory cannot apply these), ignored, and planToken. Show the plan to the user before syncing. localFolderPath is on the server's disk; a symbolic link that leads outside it fails with PATH_OUTSIDE_ROOT.

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>",
      "localFolderPath": "<localFolderPath>"
    },
    "name": "plan_sync"
  }
}

Input Schema

NameRequiredDescriptionDefault
ignoreNoExtra gitignore-style patterns, applied after the defaults (hidden files and folders, __MACOSX/, and LaTeX build output: *.aux, *.log, *.bbl, *.blg, *.out, *.toc, *.synctex.gz, *.fdb_latexmk, *.fls) and after any .olignore file in the folder; "!pattern" re-includes, for example "!.latexmkrc". Ignored paths are never uploaded, compared, or deleted, on either side.
verboseNoList every identical path and ignored entry instead of the first 25
projectIdYesOverleaf project ID
localFolderPathYesLocal folder on the server's own disk, synced as a whole
destinationFolderPathNoProject folder the local folder corresponds to; "" (the default) is the project root

Output Schema

NameRequiredDescriptionDefault
ignoredYes
toUploadYes
conflictsYes
identicalYes
planTokenYes
remoteOnlyYes
localFolderPathYes
destinationFolderPathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=true, but the description adds substantial behavior: binary files compare by git blob hash at no cost, each text document is read once through the project's queue, and a symlink escaping the root fails with PATH_OUTSIDE_ROOT. It also enumerates the result buckets and explains why conflicts are non-actionable, which is well beyond what the annotation conveys.

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 purpose and the scale constraint before the return-value detail, and every clause carries information. It is dense to the point of being a single long block, and the return-field enumeration slightly duplicates the output schema, but nothing is filler.

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?

For a five-parameter dry-run tool with an output schema, the definition covers scale limits, safety (nothing changes), failure modes, and the meaning of each result bucket including the non-applicable conflicts case. An agent has everything needed to call it and to interpret the response correctly.

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 would be 3, but the description adds meaning the schema lacks: localFolderPath is on the server's own disk and a symlink leading outside it fails with PATH_OUTSIDE_ROOT. It also clarifies that remoteOnly is what mirror mode would delete, tying return semantics to intent rather than parameters.

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?

Opens with a specific verb and resource ('Compare a local folder with a project folder') and immediately scopes it as a dry run ('report what sync_directory would do, changing nothing'). That phrasing distinguishes it cleanly from the sync_directory sibling without requiring the agent to open either schema.

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?

Gives an explicit scale boundary ('suits tens of documents, not thousands'), a workflow instruction ('Show the plan to the user before syncing'), and notes that conflicts reported here cannot be applied by sync_directory. The alternative tool is named along with the condition that separates the two.

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