XCut AI – Viral Content Research

Save a brand memory fact

xcut_save_memory

Use this when the user states a lasting fact about their brand (voice, audience, offer, constraint, posting schedule) so every XcutAI agent uses it from now on. Adds a new fact; never changes or removes one. Free. Do not use to change an existing fact (use xcut_update_memory) or for one-off instructions that apply only to the current request.

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": {
      "canvas_id": "<canvas_id>",
      "text": "<text>"
    },
    "name": "xcut_save_memory"
  }
}

Input Schema

Name	Required	Description	Default
`text`	Yes	The fact, in one or two sentences.
`category`	No	What kind of fact it is.	fact
`canvas_id`	Yes	Canvas id (a UUID) from xcut_list_canvases. The fact is saved to this canvas's brand.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 9, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already cover the safety profile (non-read-only, non-destructive, non-idempotent), and the description adds real context beyond them: the operation is append-only ('never changes or removes one'), it is free, and its effect is persistent and global ('every XcutAI agent uses it from now on'). It stops short of covering edge behavior such as duplicate facts or write limits, so it is strong but not exhaustive.

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 tight sentences with no filler: purpose is front-loaded, then the additive guarantee, then cost and the alternatives. Even the one-word 'Free.' carries a decision-relevant fact.

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?

All three parameters are schema-documented, alternatives are named for both conflicting operations, there is no output schema to explain, and the append-only semantics are explicit. An agent has everything needed to select and call this correctly.

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 description coverage is 100%, so the schema already documents text, category (with a 20-value enum), and canvas_id including its UUID source (xcut_list_canvases). The description's parenthetical list (voice, audience, offer, constraint, posting schedule) loosely maps to some categories but adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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+resource ('Save a brand memory fact') and immediately scopes it as additive: 'Adds a new fact; never changes or removes one.' This lets an agent distinguish it from xcut_update_memory and xcut_delete_memory 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 trigger ('when the user states a lasting fact about their brand') plus concrete examples of qualifying facts (voice, audience, offer, constraint, posting schedule). It also names two exclusions with the correct alternative for each: use xcut_update_memory to change an existing fact, and don't use it for one-off current-request instructions.

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

All XCut AI – Viral Content Research 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?