Skip to main content
Glama
Sign In

Marsell

by com.getmarsell
OverviewDiscussionsAdmin

Memory search

memory_search
Read-only

Searches what Marsell remembers about the business: facts (its name, site, description, audience, voice, whose accounts posts come from, the facts the owner confirmed and the owner's answers), the owner's own rules and preferences (these always win), and the active learnings the planning passes wrote, each with its confidence, when it was last confirmed and how much evidence backs it. Use it before stating what the business is or what has worked; the owner's own facts in their hand are owner_facts_read, the design language business_context_read.

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": {
      "q": "<q>"
    },
    "name": "memory_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesWords to narrow the confirmed facts, answers, rules and learnings by: one is kept when it holds any word of three letters or more, any case. The business's name, site, audience and voice always come back. null returns everything.
projectNoThe project's id or exact name. Optional when the account has one project.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already establish read-only, non-destructive, closed-world behavior, so the bar is lower; the description still adds real semantics — owner rules 'always win' over other memory, learnings carry confidence, last-confirmed time and evidence volume, and certain fields always return regardless of query. It doesn't state result limits or ordering, which keeps it off a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

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

Front-loaded with the core statement, but the opening sentence is a dense run-on carrying two long parenthetical enumerations that are slow to parse. The content earns its place, but the packaging costs readability.

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?

No output schema exists, and the description compensates by describing what comes back (facts, rules, learnings with confidence, recency, evidence volume) as well as which fields are unconditional. For a two-parameter read tool with full annotation coverage this is nearly sufficient; only result-size and ordering behavior are 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%, and the schema itself already explains q's word-matching rule, the always-returned fields, the null-means-everything behavior, and project being optional for single-project accounts. The description largely restates that surface, adding scope ('what Marsell remembers about the business') rather than new parameter mechanics, so baseline 3 applies.

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?

Specific verb (searches) plus a precisely enumerated resource: confirmed facts, owner rules/preferences, and active learnings with confidence, recency and evidence counts. It also names two sibling tools (owner_facts_read, business_context_read) and states how this differs from them, so the agent can separate them without opening a schema.

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

Usage Guidelines5/5

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

Gives an explicit use condition ('Use it before stating what the business is or what has worked') and routes two adjacent needs elsewhere: owner-supplied facts to owner_facts_read and design language to business_context_read. Exclusions and alternatives are both stated, not inferred.

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

All Marsell toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources