Skip to main content
Glama
timgordontg

engrim

by timgordontg
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

engrim_recall

Query project memory to recall architectural decisions, technical facts, user feedback, and state before starting work. Uses hybrid keyword and semantic ranking for relevant results.

Instructions

Read-only query: Search this project's engrim memory for records relevant to a query using hybrid BM25 keyword and semantic vector ranking. Use before starting non-trivial work to recall prior architectural decisions, technical facts, user feedback, and project state. Safe to invoke repeatedly with zero mutations or side effects.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kNoMaximum number of records to return (default 5).
tagNoOptional filter by tag name (e.g. 'auth', 'database').
typeNoOptional filter by memory type ('decision', 'fact', 'feedback', 'state', 'reference', 'user').
queryYesFree-text topic or search keywords.
projectNoProject identifier tag; 'auto' infers from current working directory repository root.auto
include_staleNoInclude superseded or retired records alongside active records.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countYes
projectYes
recordsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.4.6
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "description": "Ranked memory records matching the query.",
+  "properties": {
+    "count": {
+      "type": "integer"
+    },
+    "project": {
+      "type": "string"
+    },
+    "records": {
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "required": [
+    "project",
+    "count",
+    "records"
+  ],
+  "type": "object"
+}
  2. Changed6 schema fields changedv1.4.2
    • changedInput schema / properties / include_stale / description
      Previous value: -"Include superseded/archived records."New value: +"Include superseded or retired records alongside active records."
    • changedInput schema / properties / k / description
      Previous value: -"Max records to return."New value: +"Maximum number of records to return (default 5)."
    • changedInput schema / properties / project / description
      Previous value: -"Project tag; 'auto' = current working directory."New value: +"Project identifier tag; 'auto' infers from current working directory repository root."
    • changedInput schema / properties / query / description
      Previous value: -"Free-text topic to search for."New value: +"Free-text topic or search keywords."
    • changedInput schema / properties / tag / description
      Previous value: -"Optional: filter records by tag (e.g. 'auth')."New value: +"Optional filter by tag name (e.g. 'auth', 'database')."
    • changedInput schema / properties / type / description
      Previous value: -"Optional: restrict to one record type."New value: +"Optional filter by memory type ('decision', 'fact', 'feedback', 'state', 'reference', 'user')."
  3. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and does so well: it declares read-only behavior, zero mutations, no side effects, safe repeated invocation, and explains the hybrid BM25 plus semantic vector ranking mechanism. This goes beyond a simple 'search' claim and gives the agent confidence about side-effect safety.

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?

Three short, dense sentences front-load the core purpose, then add usage timing, recalled content types, and safety guarantees. Every sentence earns its place with no fluff or repetition.

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?

The presence of an output schema covers return-value details, while the description covers purpose, ranking behavior, safe usage, and intended timing. Combined with complete parameter documentation, the agent has everything needed to decide when and how to invoke the tool.

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?

The input schema already documents all six parameters with 100% coverage, including defaults and enums. The description adds high-level context about ranking, but no parameter-specific semantics beyond what the schema provides, so a baseline score of 3 is appropriate.

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?

The description opens with 'Read-only query: Search this project's engrim memory for records relevant to a query,' giving a specific verb, resource, and operation. It clearly distinguishes itself from sibling tools like engrim_add and engrim_review by framing recall as a non-mutating search.

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 explicitly advises using the tool before starting non-trivial work to recall architectural decisions, facts, feedback, and project state. It does not explicitly contrast with alternatives or state when not to use it, but the intended context is clear enough.

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