Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Word Document MCP Server create a meeting agenda with headings and bullet points"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that enables AI assistants like Claude to create and manipulate Microsoft Word documents (.docx files) programmatically.
🎨 Rich Text Formatting - Bold, italic, underline, colors, fonts, and sizes
📑 Document Structure - Headings (5 levels), paragraphs, lists, and tables
🔍 Find & Replace - Text search and replacement with regex support
📊 Tables - Create formatted tables with headers and data rows
💾 Document Management - In-memory tracking with persistent file saving
Related MCP server: MCP Word Commander
Add this to your Claude Desktop configuration:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"word-document": {
"command": "npx",
"args": ["-y", "word-document-mcp-server"]
}
}
}create_document - Create a new Word document
save_document - Save document to disk
add_heading - Add headings (levels 1-5)
add_paragraph - Add formatted paragraphs
add_bullet_list - Create bulleted lists
add_numbered_list - Create numbered lists
add_table - Insert tables with headers
find_and_replace - Search and replace text
apply_text_formatting - Format specific text
get_document_structure - View document outline
MIT
Bibash Kattel
Add a bulleted list to the document
| Name | Required | Description | Default |
|---|---|---|---|
| docId | Yes | Document identifier | |
| items | Yes | Array of list items |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It implies a mutation ('Add') but does not specify whether this requires write permissions, how it affects document structure, or if there are limitations like list length. This leaves significant gaps in understanding the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It is appropriately sized and front-loaded, making it easy to understand quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete for a mutation tool. It does not address behavioral aspects like permissions, effects on the document, or error conditions, leaving the agent with insufficient context for reliable use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, clearly documenting both parameters ('docId' and 'items'). The description adds no additional meaning beyond what the schema provides, such as format details or examples, so it meets the baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Add') and resource ('bulleted list to the document'), making the purpose immediately understandable. However, it does not distinguish this tool from its sibling 'add_numbered_list' beyond the type of list, missing explicit differentiation that would warrant a score of 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'add_numbered_list' or 'add_paragraph', nor does it mention prerequisites such as requiring an existing document. It simply states what the tool does without contextual usage information.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add a heading to the document at specified level (1-5)
| Name | Required | Description | Default |
|---|---|---|---|
| docId | Yes | Document identifier | |
| text | Yes | Heading text | |
| level | Yes | Heading level (1=Heading1, 2=Heading2, etc.) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden but offers minimal behavioral insight. It implies a write operation ('Add') but doesn't disclose permissions needed, whether changes are immediate or require 'save_document', what happens on invalid input (e.g., duplicate headings), or error behavior. The level range constraint is already in the schema, so this adds little beyond basic intent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that front-loads the core action and key constraint (level range). There's zero wasted verbiage, and every word earns its place by specifying the tool's essential function.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description is incomplete. It doesn't address what the tool returns (e.g., success confirmation, heading ID), error conditions, dependencies on other tools (like 'save_document'), or how it integrates with the document structure. Given the complexity of document editing and sibling tools, more context is needed for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all three parameters (docId, text, level) with clear descriptions and constraints. The description adds no additional parameter semantics beyond what's in the schema, but doesn't need to compensate for gaps, meeting the baseline for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Add a heading') and resource ('to the document') with specific scope ('at specified level (1-5)'), making the purpose immediately understandable. However, it doesn't explicitly distinguish this from sibling tools like 'add_paragraph' or 'apply_text_formatting' in terms of heading-specific functionality.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'add_paragraph' for regular text or 'get_document_structure' for viewing headings. There's no mention of prerequisites (e.g., document must exist), sequencing (e.g., use after 'create_document'), or contextual constraints.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add a numbered list to the document
| Name | Required | Description | Default |
|---|---|---|---|
| docId | Yes | Document identifier | |
| items | Yes | Array of list items |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool adds a numbered list but does not cover critical aspects like whether this is a mutating operation, how it affects document structure, error conditions, or response format. This leaves significant gaps in understanding the tool's behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, direct sentence with no wasted words, making it highly concise and front-loaded. It efficiently communicates the core purpose without unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and output schema, the description is incomplete for a mutating tool. It does not address behavioral traits, error handling, or return values, leaving the agent with insufficient context to use the tool effectively beyond basic parameter input.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, clearly documenting both parameters ('docId' and 'items'). The description does not add any additional meaning beyond the schema, such as examples or constraints, but the schema provides adequate baseline information, justifying a score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Add') and the resource ('numbered list to the document'), making the purpose unambiguous. However, it does not differentiate from sibling tools like 'add_bullet_list' or explain what distinguishes a numbered list from other list types, which prevents a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'add_bullet_list' or 'add_paragraph'. The description lacks context about prerequisites (e.g., document must exist) or typical use cases, offering minimal usage direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add a paragraph of text to the document
| Name | Required | Description | Default |
|---|---|---|---|
| docId | Yes | Document identifier | |
| text | Yes | Paragraph text | |
| formatting | No | Optional formatting options |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool adds text but doesn't describe where in the document it's added (e.g., at end, at cursor), whether it's a mutation that requires save_document to persist, what happens on error, or any permissions needed. This leaves significant gaps for a write operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that states the core functionality without waste. It's front-loaded and appropriately sized for a tool with clear parameters in the schema.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description is incomplete. It doesn't address behavioral aspects like placement, persistence, or error handling, nor does it explain return values. Given the complexity of adding content with optional formatting, more context is needed for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters (docId, text, formatting) thoroughly. The description adds no additional meaning beyond implying 'paragraph' relates to the text parameter, but doesn't clarify formatting usage or parameter interactions. Baseline 3 is appropriate as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('add') and resource ('paragraph of text to the document'), making the purpose immediately understandable. It distinguishes this from sibling tools like add_bullet_list or add_heading by specifying it's for paragraphs, though it doesn't explicitly contrast with alternatives like apply_text_formatting.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., document must exist), when to choose add_paragraph over apply_text_formatting or other content-adding tools, or any constraints on usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add a table to the document
| Name | Required | Description | Default |
|---|---|---|---|
| docId | Yes | Document identifier | |
| headers | Yes | Table header row | |
| rows | Yes | Table data rows |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action ('Add a table') but lacks details on permissions needed, whether this modifies the document in place, error handling, or response format. This is a significant gap for a mutation tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, direct sentence with zero wasted words, making it highly efficient and front-loaded. It immediately conveys the core action without unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity as a mutation operation with no annotations and no output schema, the description is incomplete. It doesn't address behavioral aspects like side effects, return values, or error conditions, leaving gaps that could hinder an AI agent's correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, documenting all three parameters (docId, headers, rows) clearly. The description adds no additional meaning beyond the schema, such as format examples or constraints, so it meets the baseline for high schema coverage without compensating further.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Add') and resource ('a table to the document'), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'add_bullet_list' or 'add_paragraph', which also add content to documents, so it misses full sibling distinction.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'add_bullet_list' or 'add_paragraph', nor does it mention prerequisites like needing an existing document. The description implies usage for adding tables but offers no context on exclusions or specific scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Apply formatting to specific text in the document
| Name | Required | Description | Default |
|---|---|---|---|
| docId | Yes | Document identifier | |
| searchText | Yes | Text to format | |
| formatting | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It implies a mutation operation ('apply formatting'), but doesn't specify whether this requires write permissions, if changes are reversible, potential side effects, or error conditions. For a tool that modifies documents, this lack of detail is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's function without unnecessary words. It's front-loaded and wastes no space, making it easy for an agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a document formatting tool with 3 parameters, no annotations, no output schema, and moderate schema coverage, the description is insufficient. It doesn't address behavioral aspects like permissions or side effects, provide usage context, or detail parameter nuances, leaving critical gaps for effective tool invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 67%, with 'docId' and 'searchText' well-described, but 'formatting' object properties lack descriptions. The description adds no parameter semantics beyond the schema, such as explaining how 'searchText' matches text or what 'highlight' color values are valid. Since coverage is moderate, the baseline is 3, but it doesn't compensate for the gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'apply' and the resource 'formatting to specific text in the document', making the purpose understandable. However, it doesn't explicitly distinguish this tool from sibling tools like 'find_and_replace' or 'add_heading', which might also involve text manipulation in documents, so it misses full sibling differentiation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, such as needing an existing document, or compare it to siblings like 'find_and_replace' for text modifications or 'add_heading' for structural changes, leaving the agent to infer usage from context alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Create a new Word document with optional title
| Name | Required | Description | Default |
|---|---|---|---|
| filepath | Yes | Full path where document will be saved (e.g., /path/to/document.docx) | |
| title | No | Optional title for the document |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool creates a document, implying a write operation, but lacks details on permissions required, whether it overwrites existing files, error handling (e.g., invalid filepaths), or response format. This leaves significant gaps for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero wasted words. It front-loads the core purpose ('Create a new Word document') and includes the key optional parameter, making it appropriately sized and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description is incomplete. It doesn't explain what happens after creation (e.g., does it return a document ID, save automatically, or require 'save_document'?), error conditions, or interactions with sibling tools, leaving the agent with insufficient context for reliable use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents both parameters fully. The description adds minimal value by mentioning the 'title' parameter as optional, but doesn't provide additional context beyond what's in the schema (e.g., format examples for 'filepath' or default behavior if 'title' is omitted).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Create a new Word document') and resource ('Word document'), with the optional 'title' parameter mentioned. However, it doesn't differentiate from sibling tools like 'add_paragraph' or 'save_document' which also modify documents, making it less specific than a perfect score would require.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., whether a document must be open first), exclusions, or relationships with sibling tools like 'save_document' for saving existing documents or 'add_paragraph' for modifying content.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find and replace text in the document
| Name | Required | Description | Default |
|---|---|---|---|
| docId | Yes | Document identifier | |
| findText | Yes | Text to find | |
| replaceText | Yes | Text to replace with | |
| replaceAll | No | Replace all occurrences (true) or just first (false) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. 'Find and replace text' implies a mutation operation, but it doesn't disclose behavioral traits like whether changes are immediate or require saving, if it affects formatting, error conditions, or permissions needed. This leaves significant gaps for a tool that modifies documents.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero waste. It's front-loaded and appropriately sized for the tool's complexity, making it easy to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (a mutation operation with 4 parameters), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what happens after replacement (e.g., success indicators, error handling), leaving the agent with insufficient context for reliable use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters (docId, findText, replaceText, replaceAll). The description adds no additional meaning beyond what's in the schema, such as examples or edge cases. Baseline 3 is appropriate when schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('find and replace text') and resource ('in the document'), making the purpose immediately understandable. It doesn't specifically distinguish from sibling tools like 'apply_text_formatting' or 'save_document', but the core functionality is well-defined.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., document must exist), exclusions, or comparisons to sibling tools like 'apply_text_formatting' for other text modifications.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the structure/outline of the document (headings and paragraphs)
| Name | Required | Description | Default |
|---|---|---|---|
| docId | Yes | Document identifier |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It states the tool retrieves structure/outline but doesn't disclose behavioral traits like whether it's read-only (implied by 'Get' but not explicit), error handling (e.g., invalid docId), permissions needed, rate limits, or output format (e.g., JSON list). For a tool with zero annotation coverage, this is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence with zero waste. It's front-loaded with the core purpose and specifies included elements (headings and paragraphs) without unnecessary details, making it easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (simple read operation), lack of annotations, and no output schema, the description is incomplete. It doesn't explain what the structure/outline looks like (e.g., hierarchical list), error cases, or dependencies. For a tool with no structured output documentation, more context is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with the single parameter 'docId' documented as 'Document identifier'. The description adds no additional meaning beyond this, such as format examples (e.g., UUID) or constraints. Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Get' and the resource 'structure/outline of the document', specifying it includes 'headings and paragraphs'. This distinguishes it from siblings like 'add_heading' or 'add_paragraph' which are write operations, but it doesn't explicitly differentiate from potential read siblings (none listed).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., document must exist), exclusions, or comparisons to other tools like 'find_and_replace' for content search. Usage is implied only by the tool name and purpose.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Save the document to disk
| Name | Required | Description | Default |
|---|---|---|---|
| docId | Yes | Document identifier |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It states 'Save the document to disk' but does not clarify if this is a write operation, what permissions are needed, whether it overwrites existing files, or any side effects like file format changes. This leaves critical behavioral traits unspecified.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no wasted words. It is front-loaded and efficiently conveys the core action, making it highly concise and well-structured for its simplicity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool that performs a write operation (implied by 'save') with no annotations and no output schema, the description is incomplete. It lacks details on behavior, error handling, or what happens after saving (e.g., file path, confirmation). Given the complexity and missing structured data, more context is needed for effective use.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with 'docId' documented as 'Document identifier'. The description adds no additional meaning beyond this, such as explaining the format or source of the ID. Given high schema coverage, the baseline score of 3 is appropriate as the schema handles parameter documentation adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the action ('Save') and resource ('the document'), which provides a basic purpose. However, it lacks specificity about what 'save' entails (e.g., overwrite, create new file, format) and does not distinguish it from sibling tools like 'create_document' or 'apply_text_formatting', making it vague in context.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives. It does not mention prerequisites (e.g., document must exist), exclusions, or comparisons to siblings like 'create_document' for new documents or 'get_document_structure' for viewing, leaving the agent with no usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
add_bullet_listadd_headingadd_numbered_listadd_paragraphadd_tableapply_text_formattingcreate_documentfind_and_replaceget_document_structuresave_documentEach tool has a clearly distinct purpose targeting specific document operations, such as adding different elements (bullet list, heading, table), applying formatting, or managing the document lifecycle. There is no overlap that would cause confusion—for example, add_bullet_list and add_numbered_list are clearly differentiated by list type, and apply_text_formatting is separate from content addition tools.
All tool names follow a consistent verb_noun pattern using snake_case, such as add_paragraph, apply_text_formatting, and save_document. This uniformity makes the set predictable and easy for agents to understand and navigate without any deviations in style or convention.
With 10 tools, the server is well-scoped for a Word document manipulation domain, covering core operations like creation, editing, formatting, and saving. Each tool earns its place by addressing a specific need without being excessive or insufficient for typical document workflows.
The tool set provides comprehensive coverage for basic document creation and editing, including CRUD-like operations (create, add, save) and utilities like find_and_replace. A minor gap is the lack of tools for deleting or modifying existing elements (e.g., remove_paragraph or edit_table), but agents can work around this using available tools for most tasks.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Create and manage documents, spreadsheets, and presentations from your AI assistant.
Create real Word .docx files from your AI chat: proposals, quotes, contracts, statements of work.
Use your own Word templates to convert Markdown → DOCX/PDF/HTML from any MCP-compatible AI.
Collaborative word processor you can use with your agent.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/bibash44/word-documet-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
