Skip to main content
Glama

Reflect / synthesize an answer

memory_reflect
Read-onlyIdempotent

Synthesize a reasoned answer from stored memories and return supporting evidence for a query, without saving the generated answer.

Instructions

Synthesize a reasoned answer from stored memories, with evidence. The answer is not stored.

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": {
      "query": "<query>"
    },
    "name": "memory_reflect"
  }
}

Input Schema

NameRequiredDescriptionDefault
bankNoOptional bank / user_id / dataset scope
limitNoMax evidence items where supported
queryYesQuestion to answer from memory

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.8.0
    • addedInput schema / properties / bank / description
      Added value: +"Optional bank / user_id / dataset scope"
    • addedInput schema / properties / limit / description
      Added value: +"Max evidence items where supported"
    • addedInput schema / properties / query / description
      Added value: +"Question to answer from memory"
  2. First observedv0.6.3

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so safety is covered. The description adds a genuinely non-derivable behavioral fact — 'The answer is not stored' — which tells the agent the synthesis is ephemeral and must be re-run or captured separately. It stops short of describing cost, latency, or what 'evidence' 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.

Conciseness5/5

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

Two sentences, zero filler, and the key constraint (answer is not persisted) is placed where it will be read. Nothing repeats the title or the schema.

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 tool with no output schema, the description should say more about what comes back — 'with evidence' is the only hint at return shape, and it is vague. It also leaves the relationship between 'limit' and the evidence list undefined. Adequate to call the tool, not sufficient to predict its output.

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 description coverage is 100%, so all three parameters (bank, limit, query) are already documented in structured form. The description adds no meaning beyond the schema — it does not clarify what 'bank' scopes or how 'limit' affects evidence count. Baseline 3 applies.

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?

The description names a specific verb ('Synthesize') and resource ('a reasoned answer from stored memories'), which is clearly distinct from retrieval siblings like memory_search or memory_recall. It stops short of explicitly naming a sibling to contrast with, so the differentiation is inferential rather than stated.

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

Usage Guidelines3/5

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

The phrasing implies usage (ask a question, get a synthesized answer with evidence), but there is no explicit 'use this when...' guidance and no exclusion such as 'for raw fact lookup use memory_recall instead'. With 18 sibling tools including memory_recall, memory_search and memory_consolidate, the boundary work is left to the agent.

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