Skip to main content
Glama

What clients see: onboarding form and live dashboards

customize
Destructive

Change what the agency's clients see, in chat. Surfaces: onboarding (the onboarding form: questions, heading, intro, thank-you line, who else gets the answers, which accounts it asks for); dashboard (live client dashboards: on or off, title, intro, period, which sections show and in what order, the agency's own sections); report_email (the weekly client report's wording: subject, greeting, headings, sign-off, footer; extra people who get it; instructions for writing it); agreement (the agreement email and signing page wording); review_request (the default review request text and email); lead_form (the website lead form: its fields and your own questions, button, thank-you message, colour); pages (expired links, the page after connecting, not-found pages). Set the agency default (leave client out) or one client's own. Call it with no set first: it returns what is set now and every setting it takes; then send back only what changes. Lists (questions, sections, extra, fields) are replaced whole; phrases merge one by one. note holds anything the settings can't. The look of every client page (logo, colours, fonts, custom CSS) is report_style. A client form never asks for passwords, codes, card or bank numbers, or ID numbers.

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": {
      "surface": "<surface>"
    },
    "name": "customize"
  }
}

Input Schema

NameRequiredDescriptionDefault
setNoThe settings to change, by name (the result lists them)
resetNoSettings to put back to the default at this level, or ["all"]
clientNoOne client's own settings; leave out for the agency default every client gets
surfaceYesWhich client-facing thing to change (see the description)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / surface / description
      Previous value: -"onboarding = the form on client onboarding links; dashboard = live client dashboards"New value: +"Which client-facing thing to change (see the description)"
    • changedInput schema / properties / surface / enum
      Previous value: -[
      -  "onboarding",
      -  "dashboard"
      -]New value: +[
      +  "onboarding",
      +  "dashboard",
      +  "report_email",
      +  "agreement",
      +  "review_request",
      +  "lead_form",
      +  "pages"
      +]
  2. Added

TDQS

A4.5/5.0
Behavior4/5

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

Goes well beyond the annotations by disclosing merge semantics that matter for a destructiveHint=true tool: 'Lists (questions, sections, extra, fields) are replaced whole; phrases merge one by one', plus the reset escape hatch and the 'note' catch-all. It doesn't say whether edits go live to clients immediately, whether they're permission-gated, or how partial failures are reported, so it stops short of full disclosure, but the destructive behavior itself is explained rather than implied.

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?

Front-loaded with the action and then the surface list, followed by workflow, merge rules, and the sibling pointer — a logical order. The long parenthetical surface catalogue is dense but justified because the schema enum delegates to it. Minor cost: the surface inventory in the first paragraph and the schema enum overlap, making the text heavier than strictly necessary.

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 return-value burden and does so ('it returns what is set now and every setting it takes'). For a 4-param tool with a nested free-form `set` object, it covers the read-then-write workflow, replacement vs merge semantics, reset, and the safety constraint about never collecting passwords/codes/card or bank numbers/ID numbers. It leaves open whether changes publish immediately and how conflicts with report_style styling are resolved.

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 baseline is 3, but the enum for `surface` explicitly defers to the description ('see the description') and the description supplies the real meaning of each surface, including which sub-settings each accepts. It also clarifies `client` (leave out = agency default) and `reset` semantics ('put back to the default at this level, or ["all"]'), and the lists-vs-phrases merge rule for `set`.

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?

Opens with a specific verb and resource ('Change what the agency's clients see, in chat') and then enumerates all seven surfaces with what each controls (onboarding form fields, dashboard sections, report_email wording, agreement, review_request, lead_form, pages). This lets an agent distinguish it from report_style ('The look of every client page (logo, colours, fonts, custom CSS) is report_style') and from create_lead_form 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 Guidelines5/5

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

Gives an explicit calling sequence: 'Call it with no set first: it returns what is set now and every setting it takes; then send back only what changes.' It also states the scoping alternative ('Set the agency default (leave client out) or one client's own') and routes a related need to a different tool (styling belongs to report_style). When-to-use and when-to-use-something-else are both covered.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.