Skip to main content
Glama
Sign In
Manthan

Manthan

by kidakaka
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

recall_memory

Search agent working memory and constitutional guardrails using BM25 lexical queries with tags, namespace filters, and Git commit provenance for auditable recall.

Instructions

Lexical BM25 search across agent working memory and constitutional guardrails with Git commit SHA provenance.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "recall_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoOptional tags filter to match memories with these tags
limitNoMaximum number of memories to return per category (default: 5)
queryNoSearch query string (natural language or keywords) to match against memory content, title, tags, and namespace
namespaceNoOptional namespace filter (e.g. "backend/payments")
include_constitutionNoWhether to include high-priority constitutional guardrails (default: true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description carries the full burden and does disclose useful behavior: matching is lexical BM25 (not semantic/embedding), scope spans working memory plus constitutional guardrails, and results carry Git commit SHA provenance. It omits whether the operation is read-only, how results are ranked or ordered, and how categories are returned, which are meaningful gaps for an unannotated tool.

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?

A single front-loaded sentence with zero filler, stating method, scope, and provenance in order of importance. It is dense with jargon but every clause contributes information.

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

Completeness3/5

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

For a 5-parameter, no-required-argument tool with no annotations and no output schema, the description covers what is searched and how, but not the return shape, whether results are grouped by category, or safety profile. An agent could invoke it, but would be guessing at what comes back.

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 100%, so the baseline is 3, but the description adds real meaning by clarifying that matching is lexical BM25, which tempers the schema's claim that queries may be 'natural language'. The non-required params (tags, limit, namespace, include_constitution) are left to the schema.

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?

States a specific verb and resource ('Lexical BM25 search across agent working memory and constitutional guardrails') and adds the retrieval mechanism plus provenance, so an agent knows exactly what is being queried. It does not explicitly differentiate itself from the similar-sounding sibling fetch_by_tags_and_keywords, which keeps it from a 5.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance, and no alternatives are named despite a sibling (fetch_by_tags_and_keywords) that plausibly overlaps. The agent must infer that this is the keyword-search entry point versus tag listing or index sync.

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