Skip to main content
Glama
Sign In
LibreDesk MCP

LibreDesk MCP

by Passe12345
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

paginated_search_messages

Search conversation messages by text, apply filters, and page through results with a cursor; activity messages are excluded and only accessible conversations are returned.

Instructions

Paginated Search Messages Matches messages whose text contains the query, with filters and cursor pagination. Activity messages are excluded. Returns only messages in conversations the caller can access. Requires the messages:read permission. GET /api/v1/search/messages Tags: Search

Input Schema

NameRequiredDescriptionDefault
sortNoSort by message creation time. Defaults to `newest`. (query parameter)newest
queryYesSearch query (minimum 3 characters) (query parameter)
cursorNo`next_cursor` from the previous page. A cursor works only with the `sort` it was created with. (query parameter)
filtersNoJSON-encoded filter. Either an array of conditions that are AND-ed, e.g. `[{"model":"conversations","field":"status_id","operator":"equals","value":"1"}]`, or a group `{"logic":"AND","rules":[...]}` with at most one level of nested groups. Operators: `equals`, `not equals`, `greater than`, `less than`, `set`, `not set`, `in`, `between`, `contains`, `ilike`, `not contains`. Filterable fields: `conversations` (status_id, priority_id, assigned_team_id, assigned_user_id, inbox_id, last_message_at, last_interaction_at, last_interaction_sender, created_at, waiting_since, next_sla_deadline_at, snoozed_until, sla_policy_id, tags), `conversation_statuses` (id, name), `users` (email, external_user_id), `inboxes` (channel). Messages can also be filtered on `conversation_messages` (created_at). (query parameter)
page_sizeNoNumber of results per page (defaults to 30). Values above 100 use 100. (query parameter)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: activity messages are excluded, only conversations the caller can access are searched, and the `messages:read` permission is required. It still omits what a result contains, how cursors are obtained or expire beyond the schema note, and whether queries are case-insensitive or partial-match.

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 matching behavior, then scope exclusions, then auth, then endpoint and tags. Mostly efficient, though repeating the title as the first line and appending 'Tags: Search' and the raw route are of limited use to an agent.

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 five-parameter read tool with no output schema, the description covers the essentials an agent needs: search semantics on message text, activity exclusion, access scoping, and required permission. Only the shape of returned items is left unexplained.

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 all five parameters are already documented in detail, including the sort enum, the filter DSL, and cursor/sort coupling. The description adds only the generic phrase 'with filters and cursor pagination', which does not extend parameter meaning beyond the schema.

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 and resource: 'Matches messages whose text contains the query, with filters and cursor pagination.' The mention of cursor pagination hints at how it differs from the plain search_messages sibling, but the description never names or contrasts with that sibling explicitly.

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

Usage Guidelines3/5

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

Usage is only implied: the word 'paginated' signals this is for paging through large result sets, and the filters parameter is pointed to, but there is no explicit 'use this instead of search_messages when...' guidance or stated preconditions beyond permission.

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