Marsell

Add a brand guide or document

add_guide

Adds a document for Marsell to read with the business: a brand guide, a positioning doc, a price list. Markdown or text, from a public https url, its bytes, or as markdown text. A PDF or Word (DOCX) file is kept, but it is read only where the server runs the sandboxed reader, which getmarsell.com doesn't yet: the answer's read says whether it was read, and the guide's words sent as markdown always work. It is kept whole with the setup's materials. For files on the agent's own machine, get_upload_link gives an address to send them to from your shell, so nothing big passes through your messages.

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": "add_guide"
  }
}

Input Schema

Name	Required	Description
`url`	No	A public https address of the file. Marsell fetches it itself (public addresses only, up to 8 MB).
`title`	Yes	The guide's title.
`filename`	No	Its file name with its extension, when you have one.
`markdown`	No	Or the guide itself as Markdown.
`data_base64`	No	Or the file's bytes, base64 (as large as one MCP message carries, about 4 MB).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations only declare a non-read-only, open-world, non-destructive write; the description adds substantial context beyond that — PDF/DOCX are retained but only parsed where the sandboxed reader runs, which getmarsell.com does not yet do, and the response's read field reports whether parsing happened. It also discloses that the file is stored whole alongside the setup materials. The only gap is that it never states permissions or what happens on duplicate/overwrite.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and format options are front-loaded, but the middle sentence is a long run-on that bundles the PDF/DOCX caveat, the read-field signal, and the markdown fallback into one clause chain. The final sentence about get_upload_link is useful but reads as an afterthought rather than a routed alternative.

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?

With no output schema, the description carries the burden of describing the result and does so via the read field, and it covers format handling, retention, and the large-file escape hatch. Given a 5-parameter, 100%-documented schema, an agent has enough to call it correctly, though overwrite/duplicate behavior remains unstated.

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 parameters are already documented. The description restates the three input channels (url, bytes, markdown) without adding syntax, precedence rules, or what happens if multiple channels are supplied — it neither compensates nor regresses from the schema baseline.

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?

States a specific verb and resource ('Adds a document for Marsell to read with the business') and enumerates concrete examples (brand guide, positioning doc, price list). It does not distinguish itself from the very similar sibling add_brand_file, so an agent cannot fully disambiguate on the description alone.

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?

Gives explicit conditional routing: use url/bytes/markdown here, but for files on the agent's own machine use get_upload_link so large payloads bypass messages. It also states the safe fallback ('words sent as markdown always work'). What is missing is any guidance on when to pick this over add_brand_file or add_notes.

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

All Marsell 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.