memory

Add a rule

add_rule

Save a standing instruction about how to work with this user, so it applies in every future conversation without being repeated. The rule text is sent to LeapMemory's servers and stored in the user's account, and the user can view, edit, and delete rules in the LeapMemory app. Use this instead of remember when the user states a preference about your behaviour, a convention, or a constraint: how to write, what never to do, how to format an answer. Facts about the user and their world still go to remember. Write the rule in the user's own words, as an instruction, not as a fact about them.

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": {
      "text": "<text>"
    },
    "name": "add_rule"
  }
}

Input Schema

Name	Required	Description	Default
`text`	Yes	The rule, as one clear instruction.
`scope`	No	When it applies. Use 'always' unless the user says it is limited to one project or one kind of work, in which case use that name.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 2, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), it discloses that the text is transmitted to LeapMemory's servers, stored in the user's account, and is user-visible/editable/deletable — meaningful data-handling context for a write tool. It does not address what happens if the same rule is added twice, which matters given idempotentHint=false, so a small gap remains.

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?

Well front-loaded — purpose first, then storage/privacy, then the routing rule, then authoring guidance. Every sentence carries information, though the routing and authoring sentences overlap slightly and could be tightened into one.

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 two-parameter mutation tool with no output schema and only hints in annotations, this covers purpose, storage destination, user control, sibling routing, and text authoring style. The remaining omission is duplicate handling on repeat calls, which is minor but not covered elsewhere.

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 100%, so the baseline is 3, but the description adds real content guidance: write the rule 'in the user's own words, as an instruction, not as a fact about them', which shapes how `text` should be authored and reinforces the `remember` split. `scope` semantics are left to the schema, which already covers them adequately.

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?

States a specific verb and resource — 'Save a standing instruction about how to work with this user' — and immediately scopes it to persisting across future conversations. It explicitly contrasts with the `remember` sibling, so an agent can distinguish it from both `remember` and `list_rules`/`update_rule` without opening any 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 when: the user states a preference about behaviour, a convention, or a constraint. Gives an explicit when-not: facts about the user and their world go to `remember`. It even names the alternative tool and the routing condition that selects it, leaving nothing to inference.

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

All memory tools Inspect

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

Need Help?