Conciergr

Add or change one branch

save_branch

Destructive

Add a branch, or change one (give its id from get_overview brands[].profile.branchDirectory); every other branch stays as it is. A branch line is given to customers who ask for that branch and is treated as a staff number the assistant never replies to; leave phone empty when the branch uses the main line. Keep hours and fees in the Sheet. Billing: the first branch is included; on the SGD 89 plan (get_overview billing.perBranch true) each branch past the first adds SGD 20 a month from the next bill, never part-way through a month. Tell the person before adding one; the result's billChange gives the new monthly total.

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": {
      "name": "<name>"
    },
    "name": "save_branch"
  }
}

Input Schema

Name	Required	Description
`id`	No	A branch's id, to change that branch; leave out to add one.
`area`	No	Up to 60 characters.
`name`	Yes	The name customers use for this branch, up to 120 characters.
`brand`	No	Which assistant (its slug from get_overview `brands[].slug`). Leave out when the business has one.
`phone`	No	This branch's own line, only if different from the main line.
`address`	No	Up to 200 characters.
`payeeGroup`	No	Which payment account its customers pay into: "" for the main one, else a payment account's id.
`reviewLink`	No	This branch's own review link.
`paymentNote`	No	An extra payment instruction sent only to this branch's customers, up to 200 characters.
`ownEnquiries`	No	For a franchise or separately run branch: the assistant gives this branch's line instead of its fees, timings or bookings. Needs phone.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 2, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations flag destructiveHint=true, and the description defuses that by stating 'every other branch stays as it is' — i.e. a partial update, not a replace. It also discloses that the branch line is treated as a staff number the assistant never replies to, that billing changes only from the next bill and never part-way through a month, and that the result carries billChange.

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

Conciseness4/5

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

The core action and its add/edit discriminator are front-loaded, and each subsequent sentence carries a distinct operational fact (phone semantics, billing, confirmation). The billing sentence is dense enough to require a second read, which costs it the top score.

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 10-parameter mutation with no output schema, the description supplies the missing decision-relevant context: create-vs-update, non-destruction of other branches, monetary consequence, and where the new total appears (billChange). Minor residues like payeeGroup's effect on payouts are left to the schema.

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 already 100%, so a 3 is the baseline, but the description adds real meaning beyond the schema: the id is what turns an add into an edit, an empty phone means 'use the main line', and ownEnquiries is framed as franchise/separately-run behavior. It does not cover payeeGroup or reviewLink, so not a 5.

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?

The description opens with a specific verb+resource pair ('Add a branch, or change one') and immediately clarifies the add-vs-edit discriminator (supply the id from get_overview `brands[].profile.branchDirectory`). An agent can distinguish it from remove_branch or save_team_member without opening the schema.

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?

It gives concrete when-to-do-what rules: leave out id to add, leave phone empty when the branch uses the main line, tell the person before adding, and keep hours/fees in the Sheet (an explicit out-of-scope note). It never names a sibling tool as the alternative, which keeps it short of a 5.

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?