Skip to main content
Glama

search_workspace

Read-onlyIdempotent

Búsqueda GLOBAL en TODO el workspace de una sola vez: documentos (contenido), notas diarias, entidades del knowledge graph / Atlas (nombre y contexto), reuniones (recaps) y tareas.

Para cuando el usuario pide encontrar algo y no se sabe en qué sección vive:
- "buscá X en todo", "¿dónde mencioné Y?", "encontrá todo lo relacionado con Z"
- Cuando querés una vista completa de dónde aparece un tema/persona/proyecto en el workspace.

Búsqueda HÍBRIDA: combina significado (embeddings) con coincidencia de texto, así que encuentra
también lo que NO comparte palabras con la consulta — "tokenización de tarjetas" trae la reunión
donde se habló de "PCI-PIN". No hace falta adivinar el término exacto que usó el usuario.

Devuelve un objeto con secciones:
  documents   → [{ document_id, name, snippet }]
  daily_notes → [{ date, snippet }]
  entities    → [{ id, canonical_name, type, description }]
  meetings    → [{ id, name, date, snippet }]
  tasks       → [{ id, title, status, due_date }]
  reports     → [{ id, name, date, snippet }]
  files       → [{ id, name, snippet }]
Para el detalle completo de cada resultado usar la tool específica: get_document(document_id), get_daily_note(date), get_entity_details(id), get_meeting(id), get_task_detail(id).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_workspace"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMáximo resultados por sección (default: 8)
queryYesTexto a buscar en TODO el workspace (mínimo 2 caracteres)
workspace_idNoUUID del workspace, o su nombre tal como lo dice el usuario ('Acme', 'el personal'). Omitir = TODOS los workspaces de la persona, en una sola llamada

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: it discloses that the search is hybrid (embeddings + text match) and will surface results that share no keywords with the query, illustrated with a concrete 'tokenización de tarjetas' → 'PCI-PIN' example. It also enumerates the returned sections and their fields, which compensates for the absence of an output schema.

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 scope statement, then when-to-use, then behavior, then return shape — a sensible order. It is long, but the field-by-field return listing earns its space given no output schema exists; only the repeated emphasis on 'TODO'/'GLOBAL' in caps is slightly redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a multi-section search tool with no output schema, the definition supplies the return structure, the semantic-vs-keyword behavior, and the drill-down path to detail tools. Nothing an agent needs in order to call it correctly or interpret its response is missing.

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% and the schema already documents all three parameters, including that workspace_id accepts a name or UUID and that omitting it spans all workspaces. The description reinforces the global scope of `query` but never mentions `limit` or its per-section default, so it adds little meaning beyond the structured fields — baseline 3.

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?

Opens with a specific verb and an explicit scope ('Búsqueda GLOBAL en TODO el workspace') and enumerates the seven content types it reaches (documentos, notas diarias, entidades, reuniones, tareas, reports, files). The contrast with section-scoped lookups is built into the framing ('no se sabe en qué sección vive'), so an agent can distinguish it from search_documents/search_entities/search_daily_notes 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 concrete trigger utterances ('buscá X en todo', '¿dónde mencioné Y?', 'encontrá todo lo relacionado con Z') plus the complementary case of wanting a full view of where a topic/person/project appears. It also routes the follow-up step explicitly, naming get_document, get_daily_note, get_entity_details, get_meeting and get_task_detail for full detail, so the agent knows both when to enter and when to leave this tool.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources