Skip to main content
Glama
razvangirgiz

wazap-mcp

by razvangirgiz
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Read messages from a WhatsApp chat

read_messages
Read-onlyIdempotent

Retrieve messages from a single WhatsApp chat, oldest to newest. Page back through older history by passing the oldest message ID you already have.

Instructions

Read messages from one chat, oldest to newest.

Without before you get the most recent messages. Pass before (the oldest message_id you already have) to page further back; wazap asks the phone for older history when the local store runs out, which takes a few seconds.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum number of messages (1-200)
typesNoKeep only these message types; omit for every type. The limit counts matching messages, so ["call"] returns that many calls, not that many messages of which some are calls.
beforeNoReturn the messages immediately older than this message_id
chat_idYesChat id as returned by another tool ("<digits>@s.whatsapp.net" or "<id>@g.us"), or a phone number in international format
account_idNoRegistry account id (default, work, …). Omit to resolve from chat_id or message_id, or the default account.
include_previewsNoAttach a small JPEG of each photo, newest first, up to 12 per call, so you can see what was sent: the preview WhatsApp shipped when there is one, otherwise the photo is downloaded once and shrunk on the machine running wazap

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.15.0
    • addedInput schema / properties / account_id
      Added value: +{
+  "description": "Registry account id (default, work, …). Omit to resolve from chat_id or message_id, or the default account.",
+  "minLength": 1,
+  "type": "string"
+}
    • addedInput schema / properties / include_previews
      Added value: +{
+  "default": false,
+  "description": "Attach a small JPEG of each photo, newest first, up to 12 per call, so you can see what was sent: the preview WhatsApp shipped when there is one, otherwise the photo is downloaded once and shrunk on the machine running wazap",
+  "type": "boolean"
+}
  2. Changed1 schema field changedv0.10.0
    • addedInput schema / properties / types
      Added value: +{
+  "description": "Keep only these message types; omit for every type. The limit counts matching messages, so [\"call\"] returns that many calls, not that many messages of which some are calls.",
+  "items": {
+    "enum": [
+      "text",
+      "image",
+      "video",
+      "audio",
+      "voice",
+      "document",
+      "sticker",
+      "location",
+      "contact",
+      "poll",
+      "reaction",
+      "deleted",
+      "view_once",
+      "call",
+      "system",
+      "unknown"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}
  3. First observedv0.9.3

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already establish readOnly/idempotent/non-destructive, so the bar is lower. The description adds genuine behavioral context beyond them: default ordering, and that paging past the local store makes wazap query the phone and take a few seconds. It omits pagination termination cues (e.g. what an empty result means), so it stops short of 5.

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?

Two short sentences, front-loaded with the core action, then the paging mechanic. Every clause carries information; nothing is padding or restated from the schema.

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?

With no output schema, the description should carry return-shape burden; it states ordering and the default/most-recent behavior, which is the essential part for a read tool. It does not describe what a message record contains, so it is not fully complete for a six-parameter tool with no output schema.

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 description coverage is 100%, so the baseline is 3. The description nonetheless adds meaning over the schema's terse 'Return the messages immediately older than this message_id' by framing `before` as the oldest message_id you already have, i.e. the paging cursor. Other parameters (limit, types, include_previews) get no description-level elaboration.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (Read), resource (messages), and scope (one chat, oldest to newest), which is more than a tautology of the name/title. It does not explicitly differentiate itself from close siblings like get_recent_messages or search_messages, so the agent must infer the boundary from the ordering/paging phrasing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives clear conditional guidance: 'Without `before` you get the most recent messages' and 'Pass `before` ... to page further back'. That tells the agent when to supply the parameter, but it never names when to prefer a sibling such as search_messages or get_recent_messages, leaving the tool-selection boundary implicit.

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

Deploy Server

Other Tools