Skip to main content
Glama

list_tracked_changes

Read-only

Lists tracked changes (inserts and deletes) with their locations, authors, and revisions so they can be reviewed and then accepted or rejected. Filter by document, type, or author.

Instructions

List tracked changes (suggestions) and where they are, so they can be accepted or rejected with manage_tracked_changes. With filePath, that document is read and its list is authoritative. Without it, Overleaf's project range index only chooses which documents to read: just the documents it lists with changes are read, its change ids are never used, and it may lag or leave a document out, so name a document with filePath for an authoritative list (this matters most for history-OT documents, whose index ids are never valid). indexUnavailable: true means the deployment has no index and no document was read. type and authorId keep only matching changes; limit (default 100, at most 500) caps the changes returned across all documents, totalMatched counts every match, and truncated says some were left out. Returns documents, each with filePath, revision (pass it to manage_tracked_changes), protocol, totalChanges (every tracked change in the document, unfiltered), undecidableChanges when some changes carry no id and cannot be decided by this server, and changes: changeId, type (insert: suggested text that is visible; delete: suggested removal of text that is no longer visible), start and end (1-based line and UTF-16 column in the text read_file returns; a delete is a point, so its start equals its end), length in UTF-16 units, excerpt of the inserted or deleted text (at most excerptChars UTF-16 units, default 120, 0 for none) with excerptTruncated, authorId (an Overleaf user id, or null), an ISO timestamp, and pairedChangeId linking the insert and the delete of one replacement. Also returns trackChangesActive. Ids merge and split as the document is edited, and history-OT ids are valid only with the revision they were listed with, so list again before deciding.

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": "list_tracked_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoOnly inserts or only deletes
limitNoMost changes returned across all documents
authorIdNoOnly changes by this Overleaf user id
filePathNoOnly this document, read directly rather than through the index
projectIdYesOverleaf project ID
excerptCharsNoLongest excerpt of each change, in UTF-16 units; 0 for none

Output Schema

NameRequiredDescriptionDefault
documentsYes
truncatedYes
totalMatchedYes
indexUnavailableNo
trackChangesActiveYes

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?

The readOnlyHint=true annotation already establishes that this is a safe read, but the description adds substantial behavioral context: index limitations, invalid history-OT ids, id merge and split behavior, revision-bound id validity, and the need to list again before deciding. It also discloses truncation, totalMatched, undecidableChanges, and trackChangesActive, all beyond what the annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description front-loads its purpose and key authority caveat, but it is a very dense wall of text. It spends many words enumerating return fields, including changeId, start and end, excerpt, authorId, and pairedChangeId, even though an output schema exists, so not every sentence earns its place.

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 complex read tool with index reliability caveats and revision-bound ids, the description covers the operational behavior an agent needs before calling it. Given that an output schema exists, the return-value detail is overcomplete rather than missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema description coverage is 100%, the description adds meaning the schema alone does not: filePath makes the result authoritative rather than index-based, limit caps changes across all documents, and type and authorId act as filters. It also clarifies excerptChars unit sizing and default behavior, so it meaningfully supplements the schema.

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 description begins with a specific verb and resource: it lists tracked changes and their locations, and it explicitly distinguishes this from manage_tracked_changes, which accepts or rejects them. An agent can identify the tool's role and main sibling without opening a 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?

The description makes the filePath decision explicit: without filePath, the project range index only chooses documents to read and may lag or omit a document; with filePath, that document is read directly and its list is authoritative. It also explains indexUnavailable and recommends naming a document with filePath for an authoritative list, especially for history-OT documents.

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