Frank

Change a Frank website widget

configure_embed

Idempotent

Changes one widget format's settings: intro copy, button labels, the floating launcher's position, how participants are identified, consent options and appearance. Only the fields you pass change, and the other formats are left alone. Protected domains and the on/off switch cannot be changed here — the user changes those in the Frank dashboard. Returns the full configuration and snippet; snippetChanged says whether the snippet already on the site has to be replaced.

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": {
      "researchId": "<researchId>",
      "type": "<type>"
    },
    "name": "configure_embed"
  }
}

Input Schema

Name	Required	Description
`type`	Yes	Which widget format: floating, inline or popup.
`connect`	No	Variable mode only: which user fields the snippet passes.
`consent`	No
`appearance`	No
`researchId`	Yes	The Frank research ID, as returned by list_researches.
`identityMode`	No	How participants are identified. email: the widget asks for their name and email. anonymous: nothing is collected. variable: the host page passes its signed-in user through Frank('identify').
`floatingAlign`	No	Floating widget only: where the launcher sits.
`startingContent`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 30, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well beyond the annotations (readOnly=false, idempotent=true, destructive=false) by disclosing PATCH-style semantics — 'Only the fields you pass change, and the other formats are left alone' — plus which fields are out of scope and what the response contains. It also explains snippetChanged's operational meaning, which is exactly the kind of consequence-level detail an agent needs before calling a mutation.

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?

Four short sentences, front-loaded with purpose before the partial-update rule, the exclusions, and the return shape. No filler and no restatement of the name or title.

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?

There is no output schema, and the description covers the return value (full configuration plus snippet) and the meaning of snippetChanged, which is the key state an agent needs. Minor gap: it doesn't indicate whether the newly returned snippet must be re-embedded by the caller or clarify nested connect.* fields, but nothing critical is missing.

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 63%, and the description compensates at the group level by mapping prose to parameter families (intro copy → startingContent, launcher position → floatingAlign, participant identification → identityMode/connect, consent, appearance). It adds little per-field detail beyond the schema's own enum and hex-color documentation, so it supplements rather than replaces it.

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 and resource — 'Changes one widget format's settings' — then enumerates the changeable surface (intro copy, button labels, launcher position, identity, consent, appearance). It scopes the operation to a single format's configuration, which cleanly separates it from get_embed/list_embeds (reads) and from dashboard-only settings.

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 clearly establishes when this tool applies (editing an existing widget format's configuration) and draws an explicit boundary: protected domains and the on/off switch 'cannot be changed here — the user changes those in the Frank dashboard.' It does not name get_embed as the read counterpart, so alternatives are implied rather than stated, but the exclusions are unusually concrete.

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

All Frank 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?