Generates WhatsApp links (wa.me) pre-filled with a composed reply message for manual sending via WhatsApp.
Click on "Deploy 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., "@customer-replies-mcp-server Write a reply to Ahmed about his iPhone 13 repair status, delivery tomorrow 5pm"
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.
خادم MCP لإدارة وتوليد ردود العملاء لمحل صيانة الهواتف النقالة وأجهزة الكمبيوتر. يعمل مع Claude Desktop و Claude Code وأي عميل MCP آخر.
MCP server for managing and composing customer replies for a phone & computer repair shop. Arabic-first with English variants.
Tool | الوظيفة |
| عرض تصنيفات الردود وعدد القوالب في كل تصنيف |
| البحث في القوالب بالكلمة، التصنيف، اللغة، أو النبرة |
| جلب قالب كامل مع المتغيرات |
| تعبئة قالب بقيم حقيقية وإرجاع رد جاهز للإرسال |
| تحويل رد (من قالب أو نص حر) إلى رابط |
| إضافة قالب جديد (المتغيرات تُستخرج تلقائياً من النص) |
| تعديل قالب موجود |
| حذف قالب نهائياً |
Related MCP server: whatsapp-mcp-server
greeting, price_inquiry, diagnosis, repair_status, ready_for_pickup, delay_apology, warranty, complaint, unrepairable, data_disclaimer, part_unavailable, location_hours, payment, follow_up
17 قالباً جاهزاً مضمّناً (عربي + إنجليزي) تغطي: الترحيب، التسعير، نتيجة الفحص، تحديث الحالة، جاهزية الاستلام، الاعتذار عن التأخير، الضمان، الشكاوى، تعذر الإصلاح، إخلاء مسؤولية البيانات، قطع الغيار، الموقع والأوقات، الدفع، والمتابعة بعد التسليم.
npm install
npm run buildclaude_desktop_config.json أو .mcp.json:
{
"mcpServers": {
"customer-replies": {
"command": "node",
"args": ["/ABSOLUTE/PATH/customer-replies-mcp-server/dist/index.js"],
"env": {
"REPLIES_DATA_PATH": "/ABSOLUTE/PATH/data/templates.json"
}
}
}
}Claude Code:
claude mcp add customer-replies -- node /ABSOLUTE/PATH/customer-replies-mcp-server/dist/index.jsالقوالب تُحفظ في ملف JSON. المسار الافتراضي: ~/.customer-replies/templates.json. يُغيّر عبر متغير البيئة REPLIES_DATA_PATH. عند أول تشغيل يُنشأ الملف بالقوالب المضمّنة تلقائياً.
Prompt: "اكتب رد لأحمد، جهازه iPhone 13، الحالة بانتظار قطعة الشاشة، التسليم غداً 5 مساءً"
Flow:
replies_search_templates → category: repair_status, language: ar
replies_compose_reply → template_id: status-ar-1 + variables
Output:
مرحباً أحمد 👋
تحديث بخصوص جهازك iPhone 13:
الحالة الحالية: بانتظار قطعة الشاشة
الموعد المتوقع للتسليم: غداً 5 مساءً
سنبلغك فور جاهزية الجهاز.replies_whatsapp_link يبني رابط https://wa.me/<phone>?text=<message> من قالب (template_id + variables) أو نص حر (text). العربية مدعومة بالكامل عبر ترميز UTF-8 القياسي في الرابط. فتح الرابط يفتح واتساب مع الرسالة معبّأة مسبقاً، لكن الإرسال يبقى ضغطة يدوية — لا إرسال تلقائي.
مثال: phone: "+966 5x xxx xxxx", template_id: "status-ar-1", variables: {...} → { url, text, missingVariables }.
صفحة ويب محلية بالعربية (RTL) لتصفح القوالب وتعبئتها وإرسالها عبر واتساب دون الحاجة لـ Claude أو Inspector — مخصصة لموظف المحل مباشرة.
npm run build
npm run webثم افتح http://localhost:8787 (يمكن تغيير المنفذ عبر PORT). التدفق: اختر تصنيفاً من الشريط الجانبي أو ابحث ← اضغط على القالب ← عبّئ المتغيرات وشاهد المعاينة الحيّة ← أدخل رقم العميل ← اضغط فتح واتساب لفتح محادثة واتساب مع الرسالة جاهزة (الإرسال يبقى ضغطة يدوية بشرية).
الواجهة متجاوبة مع الجوال (RTL أيضاً على الشاشات الصغيرة).
الواجهة محمية بـ HTTP Basic Auth. اسم المستخدم الافتراضي admin. إن لم تُحدَّد WEB_PASSWORD، تُولَّد كلمة مرور عشوائية وتُطبع في الطرفية عند بدء التشغيل — راقب الناتج. لتحديد بيانات دخول ثابتة:
WEB_USERNAME=shop WEB_PASSWORD=your-secret npm run webقبل كل عملية حفظ (إضافة/تعديل/حذف قالب)، يُنسخ الملف الحالي إلى <REPLIES_DATA_PATH>.bak قبل الكتابة فوقه. للاستعادة من نسخة احتياطية، أعد تسمية .bak إلى الاسم الأصلي يدوياً.
{{variable_name}} — أحرف لاتينية وأرقام وشرطة سفلية. replies_compose_reply يعيد missingVariables لأي متغير لم تُمرَّر قيمته، ويُبقي العنصر النائب في النص كما هو.
npx @modelcontextprotocol/inspector node dist/index.jsCreate a new reply template. Placeholders in body use {{variable}} syntax; variables are auto-extracted from the body.
Args:
id (string): unique slug, e.g. 'promo-ar-1'
category (string): one of greeting, price_inquiry, diagnosis, repair_status, ready_for_pickup, delay_apology, warranty, complaint, unrepairable, data_disclaimer, part_unavailable, location_hours, payment, follow_up
title (string)
language ('ar'|'en')
tone ('formal'|'friendly')
body (string): reply text with {{placeholders}}
tags (string[], optional)
Returns: the created template JSON.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Unique template id | |
| body | Yes | Reply body with {{variable}} placeholders | |
| tags | No | ||
| tone | Yes | Reply tone | |
| title | Yes | ||
| category | Yes | Template category | |
| language | Yes | Template language: 'ar' Arabic or 'en' English |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=false. The description adds valuable behavioral context, such as that placeholders use {{variable}} syntax and variables are auto-extracted from the body. This goes beyond what 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise: a clear first sentence explaining the purpose, followed by a brief note on placeholders, then a compact argument list. No superfluous text; every part contributes to understanding.
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?
The tool has 7 parameters, 6 required, and no output schema. The description covers purpose, parameter semantics, and placeholder behavior. It could mention return format more explicitly, but given no output schema, the note 'Returns the created template JSON' suffices.
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 71%. The description lists parameters with explanations, but many details (e.g., enums for category, tone, language) are already in the schema. It adds some value with an example for 'id', but overall it doesn't significantly enrich beyond the schema.
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 explicitly states 'Create a new reply template' and adds specific details about placeholder syntax and auto-extraction. The verb 'create' clearly distinguishes this from sibling tools like 'replies_update_template' and 'replies_delete_template'.
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 implies that this tool is for adding new templates, but does not explicitly state when to use it versus alternatives like 'replies_update_template' or 'replies_search_templates'. It lacks explicit when-not-to-use guidance or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Render a ready-to-send customer reply by filling a template's {{variables}} with real values.
Args:
template_id (string): id from replies_search_templates
variables (object): map of variable name -> value, e.g. { "customer_name": "أحمد", "device_model": "iPhone 13", "status": "بانتظار قطعة الشاشة", "eta": "غداً الساعة 5 مساءً" }
Returns: { text, missingVariables }. If missingVariables is non-empty the reply still contains raw {{placeholders}} — fill them and call again, or ask the user for the values.
Example: compose a status update in Arabic for customer أحمد about his iPhone 13.
| Name | Required | Description | Default |
|---|---|---|---|
| variables | No | Variable name -> value map. Values are inserted verbatim. | |
| template_id | Yes | Template id |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only and idempotent behavior. Description adds context about return structure (text and missingVariables) and the need for re-call if placeholders remain, which is beyond annotations.
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?
Extremely concise with no wasted words. Purpose is front-loaded, followed by clear parameter descriptions and an example.
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?
Despite no output schema, description compensates by explaining the return object with text and missingVariables. Provides a concrete example. Complete enough for a tool with 2 params.
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 coverage is 100%, but description adds value by linking template_id to replies_search_templates, providing Arabic example for variables, and explaining missing variables behavior.
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?
Description clearly states the tool renders a ready-to-send reply by filling template variables. It uses a specific verb ('render') and distinguishes from sibling tools like replies_search_templates.
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?
Provides clear guidance on using the tool after selecting a template and filling variables. Explains how to handle missing variables by calling again or asking user. Lacks explicit when-not-to-use or alternatives comparison.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Permanently delete a template by id. This cannot be undone.
Args:
id (string): template id
Returns: { deleted: boolean, id }.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Template id to delete |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds behavioral context beyond annotations, emphasizing that the deletion is permanent and irreversible, which aligns with the destructiveHint annotation and provides clarity.
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 extremely concise, front-loads the purpose, and includes args and returns in a structured format with no wasted words.
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 simple tool (one param, no output schema), the description fully covers what the agent needs: purpose, param details, and return shape, complemented by annotations.
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%, and the description repeats the same information ('id (string): template id') without adding new meaning beyond what the schema already provides.
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 (permanently delete) and the resource (a template by id), and distinguishes it from siblings like update or add.
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 explicit when-to-use or when-not-to-use guidance is provided. Usage is implied by the destructive nature and the sibling tool names, but no alternatives or exclusions are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get one template by id, including the full body with {{variable}} placeholders.
Args:
id (string): template id from replies_search_templates
Returns: full template JSON { id, category, title, language, tone, body, variables, tags, createdAt, updatedAt }.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Template id, e.g. 'status-ar-1' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, establishing safe read behavior. The description adds value by specifying that the tool returns the full body with placeholders and lists the exact fields in the return JSON ({ id, category, title, ... }), which is beyond what 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise: two short paragraphs. The first states the purpose and key feature (full body with placeholders). The second clearly lists arguments and return format. Every sentence is necessary and informative, with no fluff.
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 that annotations provide safety traits, the input schema fully documents the single parameter, and the description includes the return structure, the tool definition is complete. No output schema exists, but the description compensates by listing the return fields.
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 coverage is 100% with a description for the 'id' parameter including an example. The description adds semantic value by stating that the id comes from replies_search_templates, providing a source for the parameter and clarifying its origin.
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 tool's purpose: 'Get one template by id, including the full body with {{variable}} placeholders.' It uses a specific verb ('Get') and resource ('template by id'), and the inclusion of 'full body with placeholders' distinguishes it from sibling tools like replies_search_templates which returns a list of template summaries.
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 a usage hint: the 'id' argument should come from 'replies_search_templates', indicating a typical workflow of searching first then retrieving details. While it doesn't explicitly say when not to use, the set of sibling tools provides context. Clear guidance on parameter source is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all reply categories with template counts per category and language.
Use this first to discover what kinds of customer replies exist (greeting, price_inquiry, repair_status, ready_for_pickup, warranty, complaint, etc.).
Returns: JSON array of { category, count, languages }.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, so the description is not required to restate safety. However, it adds valuable context about the return format (JSON array with category, count, languages) and typical category examples, which is helpful beyond the annotations.
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 three sentences, each serving a distinct purpose: stating what the tool does, indicating when to use it, and describing the return format. No extraneous information, and the most critical details are front-loaded.
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 simplicity (no parameters, no output schema), the description fully covers its behavior: it lists categories with counts and languages, and it should be used as a discovery step. No additional information is necessary for 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?
There are no parameters, and schema coverage is 100%. The description does not need to add parameter information. Baseline score of 4 is appropriate for zero-parameter tools.
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 tool lists all reply categories with template counts per category and language, which is a specific verb and resource. It clearly distinguishes from sibling tools (e.g., replies_add_template, replies_search_templates) that operate on templates rather than categories.
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 explicitly suggests using this tool first to discover what kinds of customer replies exist, providing clear context. Although it does not specify exclusions or alternatives, the guidance is strong enough for an AI agent to understand when to invoke this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search customer reply templates by keyword, category, language, or tone.
Args:
query (string, optional): keyword matched against title, body, category, and tags (Arabic or English)
category (string, optional): exact category, e.g. 'repair_status', 'complaint'
language ('ar'|'en', optional)
tone ('formal'|'friendly', optional)
Returns: JSON array of template summaries { id, category, title, language, tone, variables, tags }. Use the id with replies_get_template or replies_compose_reply.
Examples:
"Find a reply for a delayed repair" -> category='delay_apology', language='ar'
"رد على شكوى" -> query='شكوى'
| Name | Required | Description | Default |
|---|---|---|---|
| tone | No | Reply tone | |
| query | No | Keyword to search for | |
| category | No | One of: greeting, price_inquiry, diagnosis, repair_status, ready_for_pickup, delay_apology, warranty, complaint, unrepairable, data_disclaimer, part_unavailable, location_hours, payment, follow_up | |
| language | No | Template language: 'ar' Arabic or 'en' English |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, so the description adds value by specifying return format (JSON array of template summaries) and providing examples. No contradictions.
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 concise and well-structured: a one-line summary, parameter definitions, return info, and examples. Every sentence is useful, and the front-loaded style helps the agent quickly grasp the tool.
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 no output schema, the description fully compensates by detailing the return format. All parameters are covered, and examples provide practical guidance. The tool is simple, and the description is comprehensive for its purpose.
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?
With 100% schema coverage, the description still adds significant meaning: it explains that query matches multiple fields in both languages, gives example categories, and clarifies language/tone options. This goes beyond the schema's brief descriptions.
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 specifies the verb 'search' and the resource 'customer reply templates', and distinguishes it from siblings like replies_get_template and replies_compose_reply. The title and first sentence set a clear purpose.
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?
It tells the agent to use the returned id with replies_get_template or replies_compose_reply, implying the tool's role in a workflow. However, it does not explicitly state when not to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Update fields of an existing template. Only provided fields change. If body changes, variables are re-extracted automatically.
Args:
id (string): existing template id
title, category, language, tone, body, tags: all optional
Returns: the updated template JSON.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Existing template id | |
| body | No | ||
| tags | No | ||
| tone | No | Reply tone | |
| title | No | ||
| category | No | ||
| language | No | Template language: 'ar' Arabic or 'en' English |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description adds non-obvious behavior: 'If body changes, variables are re-extracted automatically.' Annotations already provide idempotentHint and destructiveHint, so this is additive.
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?
Description is short, front-loaded with main action, and uses a clear bullet list. Every sentence adds value.
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 7 parameters, no output schema, and moderate complexity, description covers return value ('updated template JSON') and key behavior. Missing some nuance but adequate.
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 coverage is low (43%), but description only lists parameters as optional without explaining semantics beyond what schema already provides. Does not compensate fully for coverage 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?
Description clearly states 'Update fields of an existing template' with a specific verb and resource. Distinguishes from siblings like 'replies_add_template' and 'replies_delete_template'.
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?
Description mentions 'Only provided fields change' and auto re-extraction on body change, but does not explicitly state when to use vs alternatives or when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Compose a reply (from a template + variables, or from raw text) and wrap it in a clickable https://wa.me deep link that opens WhatsApp with the message pre-filled, ready for a human to press send. Arabic and English text both work — the text is URL-encoded as UTF-8.
Args:
phone (string): customer's phone number, any formatting accepted (spaces, +, dashes) as long as it includes the country code, e.g. '+966 5x xxx xxxx'. Non-digit characters are stripped automatically.
template_id (string, optional): template id from replies_search_templates
variables (object, optional): variable name -> value map, used when template_id is given
text (string, optional): raw message text, used instead of template_id
Provide either template_id or text (not both, not neither).
Returns: { url, text, missingVariables }. This does NOT send anything — it only builds a link. Opening the link (or the human clicking it) still requires WhatsApp to be installed/logged in on that device; sending is a manual click, nothing is sent automatically.
| Name | Required | Description | Default |
|---|---|---|---|
| text | No | Raw message text (alternative to template_id) | |
| phone | Yes | Customer phone number with country code, any formatting | |
| variables | No | Variable name -> value map | |
| template_id | No | Template id to compose from |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond annotations (readOnlyHint, idempotentHint), the description adds that the tool does not send anything, requires WhatsApp installation, and that non-digit characters in phone are stripped automatically. No contradictions with annotations.
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 well-structured with Args and Returns sections, uses clear language, and no unnecessary words. Every sentence adds value.
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?
Despite lacking an output schema, the description explicitly lists the return object fields (url, text, missingVariables). It also covers prerequisites (WhatsApp installed) and behavior (manual sending), making it fully self-contained.
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 coverage is 100% and includes descriptions, but the tool description adds significant value: phone formatting details (non-digit strip), template_id/text exclusivity, and returns structure. This goes beyond mere repetition.
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 tool composes a reply and wraps it in a clickable wa.me deep link. It explicitly says 'This does NOT send anything — it only builds a link,' distinguishing it clearly from sending tools like replies_compose_reply.
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 explicit guidance: when to use (build a link), when not (it does not send), and constraints between template_id and text. It also clarifies that WhatsApp must be installed and sending is manual.
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.
v1.0.0replies_add_templatereplies_compose_replyreplies_delete_templatereplies_get_templatereplies_list_categoriesreplies_search_templatesreplies_update_templatereplies_whatsapp_linkScored across 8 tools
Each tool has a distinct purpose: CRUD for templates, search, categories listing, composing a reply, and generating a WhatsApp link. There is no overlap or ambiguity.
All tools share the 'replies_' prefix and most follow a verb_noun pattern (e.g., replies_add_template, replies_delete_template). The exception is replies_whatsapp_link, which is a noun_noun and slightly deviates from the pattern.
Eight tools is a well-scoped number for a customer reply template management server. It covers creation, retrieval, updating, deletion, search, categories, composition, and WhatsApp integration without bloat.
The server covers the full CRUD lifecycle for templates, plus search, categories, composition, and WhatsApp linking. A direct 'list all templates' tool is missing, but the search tool with no filters likely serves that purpose.
Unified messaging MCP server: WhatsApp, Instagram, Telegram, SMS, Messenger & email support inbox
Unified inbox MCP for WhatsApp, Telegram, Email, voice — read/send messages, search, AI agents.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Send and schedule SMS and WhatsApp messages, manage contacts and templates, and track delivery.
