Skip to main content
Glama
Sign In
mcp-memoria

mcp-memoria

by lucabaello1998
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

leer_fragmento

Reads exact line ranges from an indexed file to expand a citation returned by memory search, avoiding the need to load the entire file.

Instructions

Lee líneas exactas de un archivo ya indexado. Sirve para ampliar una cita devuelta por buscar_memoria sin que el modelo tenga que leer el archivo entero.

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": {
      "archivo": "<archivo>"
    },
    "name": "leer_fragmento"
  }
}

Input Schema

NameRequiredDescriptionDefault
desdeNoPrimera línea (1-based).
hastaNoÚltima línea, máximo 200 líneas por pedido.
archivoYesRuta tal como la devolvió buscar_memoria (solo se puede leer lo que está indexado).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

A3.9/5.0
Behavior3/5

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

With no annotations supplied, the description carries the full behavioral load. The read-only nature is implied by "lee" and the indexed-only restriction is stated, but error behavior for invalid ranges, defaults when desde/hasta are omitted, and the shape of what is returned are never disclosed, leaving real gaps for a tool with zero annotation coverage.

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

Conciseness5/5

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

Two tight sentences with zero filler; the core action comes first and the motivating use case second. Nothing is redundant or buried.

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?

Wait — recalibrating: there is no output schema and no annotations, so the description should ideally hint at the return format and range-validation behavior. It covers purpose, precondition, and motivation well for a simple two-sentence definition, but the missing return/error detail is a real gap for a tool with no structured fallback, so a 3 is more accurate.

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% — the three parameters are already documented, including the 200-line cap and the 1-based indexing. The description's only added nuance, that archivo must be the path as returned by buscar_memoria, is already restated in the schema, so it adds little beyond structured data.

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?

"Lee líneas exactas de un archivo ya indexado" gives a specific verb (leer), an exact unit (líneas), and the scope constraint (solo archivos indexados). It also names the complementary tool buscar_memoria, so an agent can place it in the workflow, though it does not explicitly contrast with listar_fuentes or reindexar.

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

Usage Guidelines4/5

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

"Sirve para ampliar una cita devuelta por buscar_memoria" states the triggering situation clearly — use it after a search returns a citation you want more context on. The phrase "sin que el modelo tenga que leer el archivo entero" implicitly rules out full-file reads, but no explicit when-not or failure precondition (out-of-range lines, unindexed file) is given.

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