Skip to main content
Glama
Dosk3n

Glyph Hold MCP

by Dosk3n
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

prefetch_memories

Recall bounded active and general memory context for a message, with optional space/session filters and limits, to ground responses. Search or fetch full records when excerpts are insufficient.

Instructions

Recall bounded active and General context. Check entity and space: even nonempty recall may be insufficient. Search explicitly when needed and get full records by ID when excerpts omit required evidence.

Input Schema

NameRequiredDescriptionDefault
messageYes
space_idNo
max_charsNoMaximum character budget.
session_idNo
max_memoriesNoMaximum memories to prefetch.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed9 schema fields changedv2.2.0
    • removedInput schema / properties / agent
      Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": "codex",
-  "title": "Agent"
-}
    • changedInput schema / properties / max_chars / default
      Previous value: -1200New value: +2400
    • changedInput schema / properties / max_chars / minimum
      Previous value: -100New value: +256
    • changedInput schema / properties / max_memories / default
      Previous value: -3New value: +5
    • removedInput schema / properties / max_tokens
      Removed value: -{
-  "default": 300,
-  "description": "Maximum token estimate.",
-  "maximum": 2000,
-  "minimum": 25,
-  "title": "Max Tokens",
-  "type": "integer"
-}
    • addedInput schema / properties / session_id
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Session Id"
+}
    • addedInput schema / properties / space_id
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Space Id"
+}
    • removedInput schema / properties / summaries_only
      Removed value: -{
-  "default": true,
-  "title": "Summaries Only",
-  "type": "boolean"
-}
    • changedOutput schema / (root)
      Previous value: -{
-  "additionalProperties": true,
-  "title": "prefetch_memoriesDictOutput",
-  "type": "object"
-}New value: +null
  2. First observedv0.1.0

TDQS

C2.8/5.0
Behavior2/5

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

With no annotations, the description must carry the full behavioral burden, but it only hints at bounded recall and incomplete excerpts. It does not clarify permissions, read-only behavior, pagination/limits beyond schema fields, session effects, or what the returned context looks like.

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

Conciseness3/5

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

It is short and front-loads the recall statement, but several clauses are cryptic rather than economical. "Check entity and space" and "bounded active and General context" require inference, so the compactness costs clarity.

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

Completeness2/5

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

A five-parameter recall tool with no annotations, no output schema, and 40% schema coverage needs more disclosure than this. The description omits how results are selected, how session/space affect scope, and what an agent receives back beyond vague "excerpts."

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

Parameters2/5

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

Schema coverage is 40%, and only max_chars and max_memories are documented in the schema; message, space_id, and session_id have no descriptions. The prose mentions checking entity and space but does not explain the message input, space_id semantics, or how session_id scopes recall.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

It identifies a recall-style operation over bounded active and General context, so the resource area is visible, but "prefetch" is never plainly defined and the distinction from search_memories/list_memories is only implied. The description gestures at output being excerpts that may be incomplete, but the core purpose remains vague rather than a specific verb-plus-resource statement.

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?

It gives actionable routing guidance: check entity and space, search explicitly when recall may be insufficient, and fetch full records by ID when excerpts omit evidence. Those alternatives are named, though it does not state exactly when to choose prefetch versus starting with search_memories.

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