Skip to main content
Glama

Search Memories

montycat_semantic_search
Read-onlyIdempotent

Search stored memory by semantic meaning rather than keywords to retrieve relevant facts, documents, or past context for RAG and agent memory, ranked by similarity score.

Instructions

Search stored memory by MEANING (vector / semantic search), not keywords.

Use this to recall relevant facts, documents, or past context for RAG and agent memory. Returns the top matches ranked by similarity, each with its key, a cosine-similarity score, and the stored value.

Hybrid mode: filters, since, and until restrict WHICH memories are ranked — a hard AND constraint over indexed fields; ranking stays pure similarity. Combine them freely: "what did we decide about the index"

  • since yesterday + filters={"project": "montycat"} is one call. A filter matching nothing returns []. Requires a Montycat Semantic engine with hybrid support (>= 1.2.3); older engines ignore the filter.

Args: query: Natural-language description of what to recall. May be empty when vector supplies a precomputed query embedding. vector: Optional precomputed query embedding. It must match the keyspace's enrolled embedding space and dimensions; when set, the engine does not embed query. scope: Owner/user id to scope recall to (searches only that owner's memory, keyspace mem_). Use "shared" for the common keyspace. keyspace: Explicit keyspace override (advanced; bypasses scope). limit: Max number of results (default 5). min_score: Optional similarity floor in [-1, 1]; drops weak matches. filters: Optional metadata constraints, e.g. {"project": "x"} — only memories whose indexed fields equal these values are ranked. since: Only memories created at/after this time (ISO-8601, UTC — matches the auto-stamped _created_at). until: Only memories created before this time (ISO-8601, UTC).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo
queryNo
scopeNo
sinceNo
untilNo
vectorNo
filtersNo
keyspaceNo
min_scoreNo
Install Server

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the readOnly and idempotent annotations, the description discloses the return shape (key, cosine-similarity score, stored value), filter semantics as hard AND constraints, the empty-result behavior, and a critical engine version requirement. These behaviors are not visible from annotations alone.

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?

The description is long but justified by the tool's complexity: it front-loads the core purpose, then adds hybrid-mode behavior, engine caveat, and per-parameter guidance. Each sentence adds operational value; there is no filler.

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?

For a 9-parameter tool with no output schema, the description covers invocation semantics, result format, filter behavior, engine requirements, and edge cases like empty filter matches. An agent has enough information to select and call the tool correctly without further inference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, yet the description documents all 9 parameters in detail: query/vector mutual exclusivity, embedding space constraints, scope-to-keyspace mapping, limit default, min_score floor, filters format, and ISO-8601 semantics for since/until. This fully compensates for the schema's lack of descriptions.

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?

The description starts with a specific verb and resource: 'Search stored memory by MEANING (vector / semantic search), not keywords.' This clearly differentiates the tool from keyword-based siblings like montycat_recall and states its role in RAG and agent memory recall.

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?

It gives clear context for use ('Use this to recall relevant facts, documents, or past context') and explicitly contrasts with keyword search. However, it does not name sibling tools as alternatives or provide explicit when-not-to-use conditions beyond 'not keywords.'

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

Other Tools

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/MontyGovernance/montycat-mcp'

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