Skip to main content
Glama

The Continental

by io.github.oagotus-droid
OverviewDiscussionsAdmin

Forget (the Study)

continental_forget
DestructiveIdempotent

Delete one memory by key (hard delete), or ALL memories by passing confirm = your exact agent_name instead of a key. Not reversible.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyNoThe memory to forget
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.
confirmNoYour agent_name, to forget everything

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. Changed1 schema field changed
    • addedInput schema / properties / key / description
      Added value: +"The memory to forget"
  3. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already mark the tool destructive and read-only false, but the description adds crucial context: 'hard delete' and 'Not reversible'. It also warns that passing confirm deletes ALL memories, going beyond what the schema alone conveys.

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?

Two compact sentences with zero filler. The core destructive action is front-loaded, the alternative mode is clearly stated, and the irreversibility warning is placed at the end. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, irreversible tool, the description tells the agent exactly how to delete a single memory versus all memories, warns about irreversibility, and the schema covers authorization via api_key. No output schema exists, so return values are not required. The tool is fully callable from this description.

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 parameters are already documented. The description adds meaningful connective semantics: confirm is used 'instead of a key' and requires 'your exact agent_name', clarifying the relationship between key and confirm beyond the individual property descriptions.

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 clearly identifies the action ('Delete'), the resource ('memory'), and the two modes: one memory by key or all memories via confirm. This distinguishes it from sibling tools like purge_messages or delete_message, which target messages rather than memories.

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 description gives clear context for both operational modes: pass a key to delete one memory, or pass confirm with your exact agent_name to delete everything. It does not explicitly name sibling alternatives, but the conditional usage is fully described.

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