Skip to main content
Glama
mergestorm-mcp

mergestorm-mcp

Official

Search memory

search_memory
Read-onlyIdempotent

Search what Mergestorm remembers about you by meaning, ordered by relevance, and optionally include a repository’s memories and standing rules. Returns nothing when memory is off.

Instructions

Search what Mergestorm remembers about the user by meaning, best match first. Give repo as owner/repo to search that repository's memories and standing rules too. Returns nothing when memory is off.

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": "search_memory"
  }
}

Input Schema

NameRequiredDescriptionDefault
repoNo
limitNo
queryYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.31

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds two behavioral facts not present in structured data: results are ranked by semantic relevance, and an empty result set is returned when memory is disabled — a meaningful silent-failure signal. It omits ranking caveats and any notion of result volume or paging.

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 short sentences, front-loaded with the purpose, then the repo qualifier, then the empty-result caveat. Nothing is padded or repeated.

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 3-parameter search tool with no output schema, the description covers purpose, the repo qualifier, ranking, and the empty-case behavior. It leaves gaps on limit semantics and on the shape of returned memories (identifiers, snippets, scores), which an agent would need to use results effectively.

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 0%, so the description must carry the load; it does explain that repo takes owner/repo form and expands the corpus to that repository's memories and standing rules, and that query is matched semantically. The limit parameter, including its 1-20 range and default, is never mentioned, leaving a third of the parameters undocumented in both places.

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 what Mergestorm remembers about the user') plus the retrieval mode ('by meaning') and ordering ('best match first'), so it is clearly distinguishable from a plain list or keyword lookup. It stops short of naming a sibling such as list_memories or web_search to sharpen the boundary.

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 repo sentence gives a concrete usage condition — pass owner/repo when you want that repository's memories and standing rules included. However, there is no guidance on when to choose this over list_memories, web_search, or get_memory_mode, and no stated preconditions beyond memory being enabled.

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