Skip to main content
Glama

dialogbrain

by io.github.saloprj
OverviewDiscussionsAdmin

search_threads

Read-onlyIdempotent

Find or list chat threads/conversations — by topic, participant, unread/unanswered status, or recency. Omit query to list threads by filter. For message content use search.messages; for files use search.files. since filters by recency and pairs with only_unread / only_unanswered. Each thread names the LINE it speaks from (account: id, channel, name, phone) and whether the owner ever really wrote there (has_real_outgoing; imported history does not count). The same person can appear once per connected number — pick the thread by account, not by title, before you messages.send.

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum threads to return.
queryNoTopic/keyword to search threads for. OMIT to list threads by filter.
sinceNoISO date (YYYY-MM-DD). Only threads with any message activity since this date (recency filter, not 'unanswered'). OMIT to skip.
offsetNoNumber of threads to skip (for pagination, default: 0)
only_unreadNoLimit to threads with unread messages. OMIT to include read threads.
in_workspaceNoRun this one call in this workspace id instead of the session's. Nothing is stored; other sessions are not affected.
only_unansweredNoLimit to threads where the last message is incoming (you haven't replied). Covers 'threads I haven't replied to'. OMIT to include answered threads too.
participant_nameNoFilter to threads with this participant/contact. OMIT to include everyone (do NOT pass an empty string).
include_last_messagesNoWith only_unanswered: inline the most recent N messages (0-2) per thread so one call is enough to draft replies. Text truncated to 150 chars; full body via messages.read_history.
only_unread_on_platformNoLimit to threads unread in the account's own app on the platform (the member's LinkedIn, ...), as far as the channel reports it; only_unread is unread in this inbox. OMIT to skip this filter.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / only_unread_on_platform
      Added value: +{
+  "description": "Limit to threads unread in the account's own app on the platform (the member's LinkedIn, ...), as far as the channel reports it; only_unread is unread in this inbox. OMIT to skip this filter.",
+  "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. Added
  4. Removed
  5. Changed1 schema field changed
    • addedInput schema / properties / offset
      Added value: +{
+  "description": "Number of threads to skip (for pagination, default: 0)",
+  "minimum": 0,
+  "type": "integer"
+}
  6. Changed1 schema field changed
    • addedInput schema / properties / include_last_messages
      Added value: +{
+  "description": "With only_unanswered: inline the most recent N messages (0-2) per thread so one call is enough to draft replies. Text truncated to 150 chars; full body via messages.read_history.",
+  "maximum": 2,
+  "minimum": 0,
+  "type": "integer"
+}
  7. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is domain semantics: each result identifies the LINE it speaks from via `account`, and `has_real_outgoing` distinguishes genuine owner replies from imported history. It stops short of describing pagination behavior or the result set shape beyond those hints, which keeps it off a 5.

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 the core verb and facets, then alternatives, then caveats; nearly every sentence carries information. It runs a bit long and drifts into prescriptive advice about messages.send and `account` selection that is useful but sits late in the block.

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 10-parameter, zero-required search tool with no output schema, the description covers mode selection, sibling routing, filter interactions, and identity/dedup semantics. What it leaves out — limit/offset behavior and the overall result shape — is minor and largely recoverable from the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so per-dimension baseline is 3. The description does add cross-parameter meaning the schema cannot express — `since` pairs with only_unread/only_unanswered, and `query` omission switches to filter-listing mode — but most individual parameters are left to their schema text.

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 (find or list chat threads) plus the exact facets it searches: topic, participant, unread/unanswered status, recency. It also explicitly disclaims the message-content and file domains by naming search.messages and search.files, so the agent can separate it from siblings without opening a 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 an explicit mode switch ("Omit `query` to list threads by filter"), names two sibling alternatives and when to prefer them, and adds a downstream chaining rule (pick the thread by `account`, not title, before messages.send). This is close to a complete routing instruction.

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