Skip to main content
Glama
jagoff

MEMO MCP Server

by jagoff

memo_rerank

Read-onlyIdempotent

Reorders candidate memory hits against a query, scoring each by title and body to keep the most relevant subset for answer synthesis. Use after retrieval when you need a focused, top-ranked result set.

Instructions

Rerank candidate memory hits for a query.

Read-only. Performs no retrieval of its own (unlike memo_search) — it only reorders caller-supplied hit dictionaries, e.g. after memo_search or another retrieval source, when you need the most relevant subset ordered for answer synthesis. When reranking is disabled in this install, hits pass through in input order without scores.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hitsYesCandidate hit dicts (e.g. from memo_search); each is scored on its title plus snippet/body and returned with a 'rerank_score' field added. Non-dict entries are dropped.
queryYesQuery text the cross-encoder scores each hit against; empty returns the hits unchanged.
top_nNoKeep only the N best hits after reranking; None or a non-positive value returns all.
body_charsNoCharacter cap of each hit's snippet/body fed to the reranker.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed4 schema fields changedv4.4.6
    • addedInput schema / properties / body_chars / description
      Added value: +"Character cap of each hit's snippet/body fed to the reranker."
    • addedInput schema / properties / hits / description
      Added value: +"Candidate hit dicts (e.g. from memo_search); each is scored on its title plus snippet/body and returned with a 'rerank_score' field added. Non-dict entries are dropped."
    • addedInput schema / properties / query / description
      Added value: +"Query text the cross-encoder scores each hit against; empty returns the hits unchanged."
    • addedInput schema / properties / top_n / description
      Added value: +"Keep only the N best hits after reranking; None or a non-positive value returns all."
  2. First observedv1.0.0

TDQS

A4.9/5.0
Behavior5/5

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

Annotations provide readOnlyHint=true and idempotentHint=true; description confirms read-only and adds behavioral details: no retrieval, adds 'rerank_score' field, drops non-dict entries, and handles disabled state gracefully. No contradiction with annotations.

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 concise sentences front-load the purpose and key differentiator, then cover usage and edge case. No filler; every sentence earns its place.

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?

Given output schema exists, description need not detail return values. It covers purpose, usage, behavior (including disabled state and score addition), and interaction with parameters. Annotations and schema complement fully.

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 covers 100% of parameters with descriptions. Description adds extra meaning for hits (scored on title/snippet/body, adds rerank_score, drops non-dicts) and query (empty returns unchanged). This adds value beyond schema, justifying above baseline 3.

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?

Description starts with 'Rerank candidate memory hits for a query', specifying a clear verb and resource. It distinguishes from sibling memo_search by stating it performs no retrieval of its own, making its unique purpose explicit.

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?

Explicitly tells when to use: after memo_search or another retrieval source, for answer synthesis. Also mentions an alternative (memo_search) and explains behavior when reranking is disabled, giving clear usage boundaries.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/jagoff/memo'

If you have feedback or need assistance with the MCP directory API, please join our Discord server