Skip to main content
Glama

The Continental

by io.github.oagotus-droid
OverviewDiscussionsAdmin

Remember (the Study)

continental_remember
Idempotent

Store a persistent memory under a key, across sessions and model changes. The value MUST be sealed client-side (tcs1., AES-256-GCM with a key only you hold; the official client does it in remember()): the database refuses plaintext, so the house can never read your memory. Quota per tier (visitor 512 KB, Tourist 1 MB, Resident 25 MB, High Table 250 MB; blocks of 25 MB for Markers); a documented provenance envelope (source, created_at, confirmed, supersedes, tags) may travel INSIDE the seal (see the client's remember({provenance})): the house never sees it. max 96 KB per entry. Optionally sign canonical {"agent_name","content","key","kind":"memory","ts"} so your export carries proof of authorship.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyYesLetters, digits, dot, underscore, hyphen; e.g. "notes/2026-09" is not allowed, "notes.2026-09" is
api_keyNoYour key, when this client cannot send it as an Authorization header (e.g. a chat connector). Same rights as the header; the header wins if both are present.
contentYesSealed value: tcs1.<base64url>
signatureNoOptional Ed25519 signature over the canonical memory payload
signed_tsNoRFC 3339 seconds UTC, within 10 minutes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / api_key
      Added value: +{
+  "description": "Your key, when this client cannot send it as an Authorization header (e.g. a chat connector). Same rights as the header; the header wins if both are present.",
+  "pattern": "^tc_(live|visit)_[a-f0-9]{64}$",
+  "type": "string"
+}
  2. Changed2 schema fields changed
    • addedInput schema / properties / signature / description
      Added value: +"Optional Ed25519 signature over the canonical memory payload"
    • addedInput schema / properties / signed_ts / description
      Added value: +"RFC 3339 seconds UTC, within 10 minutes"
  3. Added

TDQS

A4.1/5.0
Behavior5/5

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

The description goes well beyond the annotations by disclosing that the database refuses plaintext, the value must be sealed client-side, quota varies by tier, per-entry size is capped, provenance can travel inside the seal, and signatures can prove authorship. This is rich behavioral context the structured annotations do not provide.

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?

The main purpose is front-loaded and every sentence adds operational detail. The text is dense and slightly parenthetical-heavy, but it avoids filler and earns its length given the security-critical behavior it must explain.

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 mutation tool with no output schema, the description covers persistence, security, quotas, size limits, provenance, and signature behavior. It omits what callers should expect on success or when a key already exists, but the idempotentHint annotation partly mitigates that gap.

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 meaningful semantics: content must be a tcs1.<base64url> sealed value, the practical limit is 96 KB, and the signature covers a canonical payload. This goes beyond the schema's type and length constraints.

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 opens with a specific verb and resource: 'Store a persistent memory under a key, across sessions and model changes.' This clearly distinguishes it from recall/list/forget siblings, and the key-based persistence model is immediately recognizable.

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

Usage Guidelines2/5

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

The description implies when to use the tool—when a memory must persist across sessions—but gives no explicit when-to-use guidance and names no alternatives or exclusions. With many memory-related siblings like continental_recall, continental_forget, and continental_memories, the agent must infer routing on its own.

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

All The Continental 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