Skip to main content
Glama

Word References and Notes

word_references
Destructive

Insert and manage Word tables of contents, figure/table lists, footnotes, endnotes, captions, bookmarks, cross-references, index entries, citations, and bibliographies in .docx files.

Instructions

Generated lists and scholarly apparatus: TOC and lists of figures and tables, footnotes and endnotes, captions, bookmarks, cross-references, index, citations, bibliography and Zotero. Plain text is word_edit. Every edit backs the file up first and saves atomically, and these ops refuse a document open in Word. Field results (TOC entries, page numbers, Word citations) fill in when Word updates fields, for example through word_app com_refresh_fields. Ops, one per line, as name(required; opt optional): what it does. file_path, live and backup are not repeated; word_help shows them:

  • manage_note(action; opt note_type text location note_id position): Insert, edit or delete a footnote or endnote, or remove orphaned note definitions (action).

  • insert_caption(text; opt table_index after_text image_id label above): Insert a numbered caption (SEQ field), 'Table N: text', above a table or below an image (image_id from list_elements; above flips either), or after the paragraph holding after_text.

  • insert_reference_list(type; opt title location options update_on_open): Insert a generated list (type): bibliography, TOC, list of figures, tables or equations, index, or glossary.

  • insert_bookmark(name, at_text; opt occurrence): Bookmark a text range by name, for cross-references, hyperlinks and the {bookmark: name} location; duplicate names are refused.

  • convert_notes(direction; opt note_id position): Convert footnotes to endnotes or back.

  • insert_cross_reference(to_bookmark, location; opt kind): Insert a cross-reference field pointing at a bookmark (create targets with insert_bookmark).

  • mark_index_entry(entry, location; opt subentry bold_page italic_page see): Mark an index entry with a hidden XE field at a location; insert_reference_list type='index' compiles the index. More ops follow, in the same format, in the op parameter's description.

Input Schema

NameRequiredDescriptionDefault
opYesThe operation to run: an op listed in this tool's description, or one of these, in the same format: - insert_citation(tag, location; opt pages suppress_author suppress_year prefix suffix): Insert a CITATION field for a stored source (tag from manage_source) at a location; it shows a placeholder until fields update. - insert_zotero_citation(item_keys, location; opt page prefix suffix db_path): Insert a REAL Zotero citation field (ADDIN ZOTERO_ITEM CSL_CITATION) at a location object position; Zotero recognizes and refreshes it. - search_zotero_library(query; opt db_path limit): Search the user's LOCAL Zotero library (read-only; the database is never modified). - manage_source(action, tag; opt source_type title year authors editors journal_name book_title publisher city pages volume issue edition institution url internet_site_title style extra_fields force): Add or delete a Word bibliography source by tag (action); deleting a cited source is refused unless force=true. - set_bibliography_style(style): Set the style Word's own citation and bibliography fields render in (APA, Chicago, MLA, IEEE, Turabian and others). - convert_citation_style(target_style; opt source_style dry_run): Convert plain-text citations and the reference list to another style; anything not fully parsed is left as is and flagged.
argsNoThe op's arguments as an object. Include file_path (the absolute .docx path) unless the op's line names other paths or the op reads no document; unknown keys are refused. word_help lists every argument.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

The annotations already mark this as destructive and non-idempotent, and the description adds important behavior: every edit backs up the file first, saves atomically, and refuses documents open in Word. It also explains that field results are deferred until Word updates fields, which is crucial for expectation setting.

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

Conciseness5/5

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

Despite its length, the structure is efficient and front-loaded: domain summary, safety/field-update behavior, then compact op definitions. The line-per-operation format is appropriate for a multi-operation tool and avoids wasted prose.

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 complex 13-operation tool with no output schema, the description covers selection, mutation safety, field-update timing, and most op semantics well. It is slightly incomplete on return values and relies on word_help for some shared argument details, but the overall operational picture is strong.

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 schema carries the formal parameter burden, but the description adds substantial op-level meaning for arguments, such as image_id usage, bookmark targets, hidden XE index fields, and which arguments are required versus optional. It does defer some common path details to word_help, which keeps it from being fully self-contained.

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 opens with a precise domain: generated lists and scholarly apparatus such as TOC, footnotes, captions, bookmarks, cross-references, index, citations, bibliography, and Zotero. It clearly distinguishes this from sibling word_edit by stating that plain text editing belongs there.

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?

It gives explicit routing guidance: plain text is word_edit, and field results populate through Word field updates such as word_app com_refresh_fields. It also warns that these operations refuse a document open in Word, which is a key usage constraint.

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