Skip to main content
Glama

Search issues

search_issues
Read-only

Busca issues por FULL-TEXT (Postgres tsvector, diccionario español) en título, descripción, comentarios Y el texto de los campos personalizados, ordenadas por relevancia (ts_rank). Cada resultado trae la issue (id, identificador TEAM-N, título, estado…) más snippet (un extracto con los términos resaltados entre …), rank y customFields (los valores de sus campos personalizados, con nombre y tipo: no hace falta pedir cada issue). También encuentra por identificador exacto (TEAM-N). Para ACOTAR por el valor de un campo usa customFields (los fieldId salen de list_custom_fields): [{fieldId, op, value}], combinables en AND con la query. Operadores por tipo — checkbox: isTrue|isFalse|empty; member: is|isNot|empty (value = userId); number: eq|gt|lt|empty; date: before|after|between|empty (value en epoch ms, between usa value2); text: contains|empty. query vacía + customFields = listado filtrado. limit opcional (1-100, por defecto 25). Para ACOTAR por etiqueta pasa labels: ids o NOMBRES de etiqueta (sin distinguir mayúsculas; list_labels las enumera). labelMatch elige 'any' (por defecto: al menos una de ellas) o 'all' (todas). Una etiqueta que no existe en el workspace es un error, no se ignora. Combinable en AND con la query y customFields. workspaceId opcional: el workspace donde operar (list_workspaces los enumera). Sin él se usa el de la credencial. Buscar un identificador (TEAM-N) SIN workspaceId busca en todos tus workspaces, porque el identificador no es único entre ellos: cada fila trae su workspace, y si salen varias tienes que elegir tú.

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_issues"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
queryYes
labelsNo
labelMatchNo
workspaceIdNo
customFieldsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / labelMatch
      Added value: +{
      +  "enum": [
      +    "any",
      +    "all"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / labels
      Added value: +{
      +  "items": {
      +    "type": "string"
      +  },
      +  "type": "array"
      +}
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnlyHint and openWorldHint=false; the description goes well beyond by disclosing the ranking (ts_rank), the result shape (issue fields + `snippet` with <mark> highlights + `rank` + `customFields`), the Spanish tsvector dictionary, the operator matrix per field type, and the identifier-non-uniqueness caveat that requires the caller to disambiguate rows by `workspace`.

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?

The most useful information (full-text search + ranking + snippet) is front-loaded and every sentence carries substance, but the whole definition is a single dense paragraph mixing query syntax, operators, label rules, and workspace caveats. Bullet points or line breaks would make scanning materially faster without adding length.

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 6-parameter read tool with no output schema, the description covers query semantics, filtering, pagination default, return payload, and the multi-workspace edge case. An agent has everything needed to construct a correct call without opening the 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 coverage is 0%, so the description must carry the load, and it largely does: limit (1-100, default 25), labels accepting ids or names case-insensitively, labelMatch any/all semantics, workspaceId fallback to the credential's workspace, and per-type operator semantics including `value2` for `between` and epoch-ms for dates. Minor gaps remain, e.g. the exact shape of `snippet` highlighting is described but not the customFields result object's structure in detail, and the schema's loose numeric bounds for `limit` are only tightened implicitly.

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?

Names the specific verb and resource ('Busca issues por FULL-TEXT') plus the indexed fields, the ranking mechanism, and a second mode (exact identifier TEAM-N). It also implicitly distinguishes itself from list_issues by describing 'query vacía + customFields = listado filtrado' and from get_issue by noting results already include customFields values.

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?

Explicit routing is given throughout: use list_custom_fields to obtain fieldId, list_labels to enumerate labels, list_workspaces for workspaceId, and empty query with customFields as a filtered list. It also states an exclusion-type rule ('Una etiqueta que no existe en el workspace es un error, no se ignora') and the cross-workspace behavior when searching an identifier without workspaceId.

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