Skip to main content
Glama

Search Second Brain

search_memories
Read-onlyIdempotent

Search stored memories from earlier coding sessions to recall past decisions, findings and notes. Filter by project to find the context you need, then read the matching memory.

Instructions

Search the user's Second Brain: decisions, findings and notes kept from earlier coding sessions, across every project or one. Returns up to 30 ranked candidates (any word matches; rarer words, and hits in a title or its English keywords, rank higher; a few synonyms such as PR/pull request, cost/price/spend and decision/rule are matched; typos are tolerated), each with kind, date, project, keywords and a short summary: judge by meaning which ones answer the question, then read one with get_memory. Titles are often in the user's own language, not English, while keywords are English. If nothing fits, rephrase and search again: other words, fewer words, a synonym, the product or component name, or words in the user's language. A memory marked superseded_by is no longer current: the id named replaces it.

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": "search_memories"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoHow many to return (default 30, at most 50).
queryNoWords to look for. Empty lists the newest memories.
projectNoKeep one project's memories (its name, e.g. the repository folder's name). Omit for all.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already cover the read-only, idempotent, non-destructive profile, and the description adds substantial behavior beyond them: the ranking signal ('rarer words, and hits in a title or its English keywords, rank higher'), fuzzy matching, synonym handling, typo tolerance, and the meaning of superseded_by. It also warns that titles are in the user's own language while keywords are English, which materially changes how an agent should phrase queries.

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?

Purpose is front-loaded in the first clause, and every sentence contributes ranking, result-shape, or follow-up guidance. It runs long as one unbroken paragraph and the ranking parenthetical is dense, but there is little true waste.

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?

There is no output schema, so the description carries the burden of describing returns, and it does: kind, date, project, keywords and a short summary, plus the superseded_by caveat and the get_memory next step. The only gap is the 30-versus-50 count ambiguity and no statement about ordering ties or what happens with zero matches beyond 'rephrase'.

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 coverage is 100%, so the baseline is 3 and the description mostly restates it ('across every project or one' maps to project, empty query listing newest is already in the schema). It also introduces a mild inconsistency: 'up to 30 ranked candidates' versus the schema's limit maximum of 50, which an agent may find confusing when setting limit.

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 ('Search the user's Second Brain') and immediately scopes it to 'decisions, findings and notes kept from earlier coding sessions, across every project or one'. That is precise enough to act on, though it never differentiates itself from the sibling search_prose, so an agent cannot tell the two apart from the text alone.

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 a concrete workflow: search, then 'read one with get_memory', and prescribes fallback strategies when results are poor ('rephrase and search again: other words, fewer words, a synonym, the product or component name, or words in the user's language'). Strong context, but no explicit exclusion such as when to prefer search_prose or current_decisions instead.

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