Skip to main content
Glama

rr_save_memory_entry

DestructiveIdempotent

Save a small JSON object under a granted namespace and key for later agent retrieval; secret and personal-contact values are refused.

Instructions

Save a small JSON object under a namespace and key, for an agent to read back later. It is not for secrets or personal data; values with obvious secret or contact-detail shapes are refused. The namespace must have been granted to this API key.

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": {
      "namespace": "<namespace>",
      "key": "<key>",
      "value": "<value>"
    },
    "name": "rr_save_memory_entry"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyYesThe entry's key within the namespace, up to 200 characters.
valueYesThe JSON object to save, up to 16 KiB.
namespaceYesA context namespace this key has been granted, for example supplier_rules.
scope_refNoOptional label for what the entry is about, up to 200 characters. Not secret.
ttl_secondsNoOptional lifetime in seconds, up to 90 days.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.3.1

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=true; the description adds real context beyond them by disclosing input validation ('values with obvious secret or contact-detail shapes are refused') and an authorization prerequisite on the namespace. The notable gap is that it never explains what makes the call destructive — presumably overwriting an existing key — which is the one behavior an agent most needs to know before saving.

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?

Three short sentences, front-loaded with the core action, then the exclusion, then the precondition — no filler or hedging. 'For an agent to read back later' is the only mildly redundant clause, but it usefully conveys the round-trip intent.

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 five-parameter write tool with full schema coverage and a complete annotation set, the description covers purpose, exclusions, and authorization. It is nearly complete; the missing piece is overwrite/idempotency semantics for an existing key, which would round out the destructiveHint profile.

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 coverage is 100%, so namespace, key, value, scope_ref, and ttl_seconds are all documented in the schema itself. The description reinforces the namespace grant constraint and the 'small JSON object' nature of value but adds no syntax, format, or limit detail beyond what the schema already states; baseline 3 applies.

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?

The description gives a specific verb and resource ('Save a small JSON object under a namespace and key') plus the intent ('for an agent to read back later'), which clearly separates it from delete/get/list memory siblings by implication. It stops short of naming the read-back counterpart (e.g., rr_get_memory_entry), so the differentiation is inferential rather than explicit.

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 states a clear exclusion ('not for secrets or personal data') and a hard precondition ('The namespace must have been granted to this API key'), which is exactly the kind of gate an agent needs before calling. It does not explicitly point to alternatives such as rr_get_memory_entry for retrieval or rr_delete_memory_entry for cleanup, leaving that to the sibling names.

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