The Marketing Vault

Save a reference note

save_reference_note

DestructiveIdempotent

Stores a text note (positioning doc, offer outline, voice guide, markdown) on a business as background for Vault generations. Saving with an existing title replaces that note; remove=true deletes it. Up to 20,000 characters per note and 30 notes per business. Does not use a generation.

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": {
      "title": "<title>"
    },
    "name": "save_reference_note"
  }
}

Input Schema

Name	Required	Description
`title`	Yes	Note title, e.g. the file name.
`remove`	No	Delete the note with this title instead of saving.
`content`	No	The note body (markdown). Required unless remove is true.
`business_profile_id`	No	Business id from list_businesses. Defaults to the default Business.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Annotations only supply flags (mutable, destructive, idempotent); the description adds quota limits the agent cannot see anywhere else: 20,000 characters per note and 30 notes per business. It also explains the replace-on-title semantics and that the call does not consume a generation, all consistent with destructiveHint=true and idempotentHint=true.

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?

Four short sentences, each carrying distinct information: purpose, overwrite/delete semantics, quotas, and cost. The core purpose is front-loaded and nothing is redundant.

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?

With no output schema and full schema coverage, the description supplies everything the agent needs: what a note is, how overwrites and deletion work, hard limits, and that no generation is consumed. Error behavior at the 30-note cap is the only minor omission.

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, and the description earns the extra point by making the title parameter the replacement key and by noting content is required only when remove is not true – a conditional requirement the schema's required list does not capture. It still does not explain formats or the default business resolution beyond what the schema states.

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?

"Stores a text note ... on a business as background for Vault generations" gives a specific verb and resource, plus the concrete content types (positioning doc, offer outline, voice guide, markdown). It does not name a sibling such as save_output, so the differentiation is implied by the note/background framing rather than stated.

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

Usage Guidelines3/5

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

The sentence "Saving with an existing title replaces that note; remove=true deletes it" tells the agent the upsert and delete paths, which is useful context for choosing how to call it. However, it never states when to prefer this tool over alternatives like save_output or update_brand_voice, nor any prerequisites.

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

All The Marketing Vault 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?