Marsell

Owner fact set

owner_fact_set

Destructive

Adds, changes or takes out one of the owner's own facts (Brand › Business › What Marsell knows, as Add a fact does there): what is true about the business, which every plan, post, page and claim check reads from then on, ahead of the facts setup confirmed. A confirmed fact that is wrong or out of date stays as it was set and is corrected by the true one here, said as a correction ("Launch: the Product Hunt launch is no longer on 27 October 2026; it comes later, and no date is set yet."); a rule is for what Marsell must or must not do, never for a fact. text alone adds a fact; id with text changes it; id with remove takes it out. Only what the owner said or a source shows, never a guess. Free. It needs an act key.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "owner_fact_set"
  }
}

Input Schema

Name	Required	Description
`id`	No	the owner's fact to change or take out, by its id from owner_facts_read
`text`	No	the fact, whole, in the owner's words or as a source shows it, with what it is about first: "Launch: the Product Hunt launch is no longer on 27 October 2026; it comes later, and no date is set yet." A new fact, or the new words of the one named by id.
`remove`	No	true takes the fact named by id out
`project`	No	The project's id or exact name. Optional when the account has one project.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare a non-read-only, destructive, closed-world write, and the description adds real context beyond that: the fact propagates to every plan, post, page and claim check afterwards, and an act key is required. It also explains that corrections replace rather than append and that the act is free, though it does not say whether removal is recoverable.

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?

The action is front-loaded, which is good, but the body is two long run-on clauses with parenthetical asides ('as Add a fact does there') and a full example embedded in prose. The combination rules and correction policy earn their place; the UI cross-reference and repeated framing do not.

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 definition covers what the call does, how parameters combine, where the effect propagates, the evidence rule, cost, and the act-key requirement. The remaining gap is what a successful or failed call returns and whether a removed fact can be restored.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

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 goes further by documenting the cross-parameter contract the schema cannot express: text alone adds, id plus text changes, id plus remove deletes. It also adds an evidence constraint on text ('only what the owner said or a source shows, never a guess') that meaningfully shapes what the agent may pass.

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 set (adds, changes, takes out) against a specific resource (the owner's own facts), and explicitly separates facts from rules so the agent knows which kind of object this mutates. It also points at owner_facts_read as the source of ids, giving a concrete sibling relationship.

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 clear when-to-use conditions: new facts, and correcting a confirmed fact that is wrong or out of date, phrased as a correction with a worked example. It also states the exclusion that rules are a different tool, though it never names the actual rule-setting sibling, so the agent must infer which tool to call for rules.

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.