Conciergr

Set the assistant's tone

set_tone

Destructive

How the assistant sounds (same knowledge, the business's voice), from the next reply: casual = friendly and relaxed, like a helpful shop owner texting back, the occasional emoji; professional = warm, competent, unhurried, a well-run front desk (the default); formal = courteous and precise, full sentences, no contractions, no emoji; very-casual = lowercase, light punctuation, like texting a friend; custom = describe the voice in customTone (paste two or three replies the team actually sends and say what to keep or drop; up to 1,800 characters).

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": {
      "tonePreset": "<tonePreset>"
    },
    "name": "set_tone"
  }
}

Input Schema

Name	Required	Description
`brand`	No	Which assistant (its slug from get_overview `brands[].slug`). Leave out when the business has one.
`customTone`	No
`tonePreset`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 2, 2026

TDQS

A3.7/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the safety bar is lower. The description contributes the genuinely useful facts that knowledge is unchanged and the change takes effect from the next reply, but it never states that the previous tone is overwritten or whether the change is per-brand.

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?

One front-loaded sentence opens with purpose, then spends the remainder on the enum definitions that actually need explaining. No filler, and the length is proportional to five presets that need differentiation.

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?

No output schema, a destructive mutation, and three params — the description covers the two undocumented params thoroughly and notes effect timing. It stops short of the overwrite/scope semantics an agent might want before a destructive write, and `brand` is omitted from the prose.

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?

With only 33% schema coverage, the description carries real weight: it documents every enum value of tonePreset and gives concrete semantics for customTone (paste real replies, state what to keep/drop, 1,800-character cap) that appear nowhere in the schema. Only `brand` is left to the schema, which does describe it.

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?

The description states precisely what the tool governs: 'How the assistant sounds (same knowledge, the business's voice)' with effect 'from the next reply'. It is unmistakably distinct from sibling setters like set_signoff and set_topics, though it never names them or explicitly says 'sets'.

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?

It marks 'professional' as the default and gives a how-to for the custom path ('paste two or three replies the team actually sends'), which implies when custom is appropriate. There is no explicit guidance on choosing between presets for a given business, and no when-not-to-use statement.

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

All Conciergr 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?