Mondovo

Export form submissions as CSV

export_submissions

Read-onlyIdempotent

Every form submission matching the filters as one CSV (the same file the Inbox's Export button produces): name, email, phone, form, status, submitted-at, source, page and UTM columns, plus one column per question asked across the forms. Formula-like cells are neutralised for spreadsheets. truncated is true when more rows matched than max_rows. PERSONAL DATA — hand it only to the user who asked for it.

Input Schema

Name	Required	Description
`form`	No	Only submissions from this form, by its slug (see list_forms)
`search`	No	Case-insensitive match on the submitter's email or name
`source`	No	"web" for the site's own forms, "agent" for enquiries sent by AI agents
`status`	No	Only submissions in this Inbox status
`site_id`	Yes	The site, from list_sites
`to_date`	No	Submitted on or before this ISO date/time
`category`	No	Only this submission category, when the site defines categories
`max_rows`	No	Most rows to include, default 1000, max 2000
`from_date`	No	Submitted on or after this ISO date/time, e.g. "2026-09-01"
`user_goal`	No	Optional: the user's goal behind this call, in one short sentence of plain words (e.g. "add a page so customers can book tables"). No names, emails or other personal details.
`include_test`	No	Include submissions made with the editor's test mode (default false)

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 30, 2026

addedInput schema / properties / user_goal

Added value: +{
+  "description": "Optional: the user's goal behind this call, in one short sentence of plain words (e.g. \"add a page so customers can book tables\"). No names, emails or other personal details.",
+  "type": "string"
+}

First observedOct 19, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already cover read-only safety, but the description adds genuine behavior the schema cannot: exact column set, per-question columns, formula neutralisation for spreadsheets, the semantics of `truncated`, and a personal-data handling constraint. These are the traits an agent needs to interpret and relay the result correctly.

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 tight paragraph: what it produces, what's in it, the safety caveat, the truncation signal, and the PII warning. No preamble, no repetition of schema fields, and the most decision-relevant clause is front-loaded.

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 the return shape well by enumerating columns and the `truncated` indicator. The one gap is delivery: it never says whether the tool returns CSV text, a file reference, or a download URL — an agent learning the result format has to guess.

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 the baseline is 3; the description earns a bump by explaining the interaction between `max_rows` and the `truncated` flag, which the parameter docs don't state. Filter parameters themselves are only referenced generically ('matching the filters'), so it doesn't fully re-document them.

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 and resource (export form submissions) plus the output shape ('one CSV'), and pins it to a concrete artifact ('the same file the Inbox's Export button produces'), which separates it from list_submissions. An agent can route between the CSV export and the row-listing sibling without opening either schema.

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?

The 'as one CSV' framing and the Inbox-Export equivalence imply this is for when the user wants a file rather than a listing, but no sibling is named and there is no explicit when-not guidance. The closest alternative, list_submissions, is left to inference.

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

All Mondovo 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?