Skip to main content
Glama

remember_preference

Store a lasting buyer preference for how to negotiate or write with sellers, such as tone, wording, or arguments to use or avoid. Use it when feedback applies to future messages, not just one.

Instructions

Save a lasting preference of the buyer about how to negotiate or write (tone, wording, opening level, arguments to use or avoid). Call it when their feedback is meant generally, not just for one message. One short rule per call, in the buyer's language.

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": {
      "rule": "<rule>"
    },
    "name": "remember_preference"
  }
}

Input Schema

NameRequiredDescriptionDefault
ruleYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden and does disclose the key trait that this is a persistent write ("lasting", applicable beyond one message), plus a granularity constraint ("one short rule per call") and a language requirement. It is silent on duplicate handling, whether similar rules are merged or overwritten, and what the call returns — meaningful gaps for a persistence tool with zero annotation coverage.

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 before the trigger condition and the per-call constraint. Every sentence contributes something distinct and there is no redundant restatement of the tool name.

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?

For a one-parameter, no-output-schema tool this covers what to save, when to save it, how atomic it should be, and what language to use — enough to call it correctly. Residual gaps around duplicate/overwrite behavior and the effect on later drafting keep it from being fully complete.

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

Parameters4/5

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

Schema coverage is 0%, so the description must define the single parameter, and it does: the rule's content domains (tone, wording, opening level, arguments), its granularity (one short rule), and its language (the buyer's language). That is substantial meaning added beyond the bare string schema; only the 300-character cap is left to the schema itself.

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 states a specific verb and resource ("Save a lasting preference of the buyer") and immediately scopes what counts as a preference: tone, wording, opening level, arguments to use or avoid. The word "lasting" also implicitly separates it from forget_preference and from one-off drafting behavior, so an agent can identify the tool without opening the schema.

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?

The trigger condition is explicit and contrastive: "Call it when their feedback is meant generally, not just for one message." That tells the agent both when to call and when not to. It falls short of 5 only because no sibling alternative is named for the one-message case, though the exclusions make the intended routing clear.

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