Skip to main content
Glama

dialogbrain

by com.dialogbrain
OverviewDiscussionsAdmin

search_messages

Read-onlyIdempotent

Search message content across all chats — semantic + keyword. Use to find what was said: quotes, topics, info exchanged. Pass direction, chat_kind or per_chat for an EXACT text search instead: who wrote it (outgoing = the owner), private chats or groups, one result per chat with the number of matches. That is the way to find the chat of a person by how the owner addresses them, e.g. query='Дима', direction='outgoing', chat_kind='dm', per_chat=true. For chats/threads themselves use search.threads; for files use search.files; for links use search.links.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMaximum messages to return.
queryNoWhat to search for in message content.
date_toNoISO8601 date (YYYY-MM-DD) upper bound. OMIT to skip.
per_chatNoExact search only: one result per chat (its newest match) with `matches` = how many messages there matched. OMIT for every message.
chat_kindNoExact search only: 'dm' = private chats, 'group' = groups and channels. OMIT for both.
date_fromNoISO8601 date (YYYY-MM-DD) lower bound. OMIT to skip.
directionNoExact search only: 'outgoing' = messages the owner wrote, 'incoming' = messages others wrote. OMIT for both.
whole_wordNoExact search only: match the query as a whole word ('Дима' finds 'Привет, Дима!' but not 'Димасик'). OMIT to match any part of a word.
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
participant_nameNoFilter to messages involving this participant/contact name. OMIT to search across everyone (do NOT pass an empty string).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / chat_kind
      Added value: +{
+  "description": "Exact search only: 'dm' = private chats, 'group' = groups and channels. OMIT for both.",
+  "enum": [
+    "dm",
+    "group"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / direction
      Added value: +{
+  "description": "Exact search only: 'outgoing' = messages the owner wrote, 'incoming' = messages others wrote. OMIT for both.",
+  "enum": [
+    "outgoing",
+    "incoming"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / per_chat
      Added value: +{
+  "description": "Exact search only: one result per chat (its newest match) with `matches` = how many messages there matched. OMIT for every message.",
+  "type": "boolean"
+}
    • addedInput schema / properties / whole_word
      Added value: +{
+  "description": "Exact search only: match the query as a whole word ('Дима' finds 'Привет, Дима!' but not 'Димасик'). OMIT to match any part of a word.",
+  "type": "boolean"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / in_workspace
      Added value: +{
+  "description": "Run this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.",
+  "type": "integer"
+}
  3. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: the tool has two distinct execution modes selected by which parameters are passed, and per_chat changes the result shape (one row per chat with a matches count). It does not mention result format details or any rate limits, keeping it just below the top.

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

Conciseness4/5

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

Front-loaded with purpose, then mode-switching, then an example, then sibling routing. Every sentence carries information, though the middle paragraph is dense and backtick-heavy, slightly compressing the reading flow.

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?

Covers the mode distinction, the exact-search trigger parameters, an example, and sibling routing. Date bounds, limit, participant_name, whole_word, and in_workspace are documented in the schema and need no restatement here, and there is no output schema to explain. Adequate for a 10-param, all-optional search tool.

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 baseline is 3, but the description adds genuine meaning beyond the schema: it explains that direction/chat_kind/per_chat collectively switch the tool into exact-text-search mode and spells out the semantic of outgoing vs incoming and per_chat's one-row-with-matches output. That cross-parameter interaction is not captured by the per-property schema text alone.

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?

States a specific verb and resource ('Search message content across all chats') plus the two retrieval modes (semantic + keyword). It explicitly distinguishes itself from search.threads, search.files, and search.links, so an agent can route without opening any 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?

Gives explicit when-to-use guidance: semantic search for quotes/topics/info, and exact text search when direction/chat_kind/per_chat are passed. It names the three sibling alternatives and their domains, plus a concrete worked example for finding a person's chat by how the owner addresses them.

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

All dialogbrain toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources