Skip to main content
Glama

membridge_recall

Read-onlyIdempotent

Retrieve and search saved user memories by keyword or category, then format them for a target AI platform before answering personalized questions or switching tools.

Instructions

Retrieve and search persisted user memories from the local portable brain (~/.membridge/brain.json). Use this before answering personalized questions or switching AI tools to recall identity, tech stack, active projects, preferences, or rules. Filter by optional keyword query and/or category, and optionally format the result for a specific target platform (e.g. claude, chatgpt, gemini, markdown, json). Returns JSON with matching memory count and items, or a formatted memory pack when target is provided.

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": "membridge_recall"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNoCase-insensitive keyword substring to match against saved memory text (omit to return all saved memories).
targetNoOptional output formatter for the recalled memories (e.g. claude, chatgpt, gemini, deepseek, markdown, json). Omit for raw structured JSON.
categoryNoRestrict results to a single memory category: identity, projects, stack, preferences, rules, or context.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.2.0
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / category / description
      Previous value: -"Optional category filter."New value: +"Restrict results to a single memory category: identity, projects, stack, preferences, rules, or context."
    • changedInput schema / properties / query / description
      Previous value: -"Optional keyword filter."New value: +"Case-insensitive keyword substring to match against saved memory text (omit to return all saved memories)."
    • changedInput schema / properties / target / description
      Previous value: -"Optional destination format (e.g. claude, markdown, json)."New value: +"Optional output formatter for the recalled memories (e.g. claude, chatgpt, gemini, deepseek, markdown, json). Omit for raw structured JSON."
  2. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: the data source is a local file and the return shape is JSON with a count plus items, or a formatted pack when target is set. It does not cover behavior when the brain file is missing or empty, which is the main remaining gap.

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?

Three sentences, front-loaded with the purpose, then usage, then parameters and return shape. No filler, though the final sentence duplicates the target enum values already listed in the schema and could be trimmed.

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

Completeness4/5

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

With no output schema, the description correctly compensates by describing the return value (count plus items, or a formatted pack). All three optional parameters are accounted for and the tool is simple, so the definition is nearly complete; only edge-case behavior (empty or absent brain file) is unaddressed.

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 are already documented in the schema, and the description largely restates them (keyword query, category, target platform). The one piece of added meaning is that query and category can be combined ('and/or'), which the schema does not spell out. Baseline 3 applies when the schema does the heavy lifting.

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 pair (retrieve and search) plus the exact resource (persisted user memories) and even the storage location (~/.membridge/brain.json). It is clearly a read path distinct from membridge_remember, but it never explicitly routes the agent away from membridge_extract or membridge_format, so sibling differentiation is implied 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 Guidelines4/5

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

Gives concrete triggering conditions: 'before answering personalized questions or switching AI tools', with the memory types to recall (identity, tech stack, active projects, preferences, rules). It does not state when NOT to use it or name an alternative tool for overlapping cases, so it stops short of full routing guidance.

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