Niches · Forms, surveys & structured intake

Summarise what respondents said

One company's docs show a full fit.

1companies, full fit
9companies, fit with a limit
10companies carry the tag
5share of the category's work
1first-hand accounts

What counts as done

A summary with counts per choice and themes from open text, from aggregate endpoints or a full paged read.

Measured, for our own tests: in under a minute. No docs we read state these figures, so they don't count against a listing here.

How agents ask for it: summarise this survey, what are the top complaints, report on this quarter's NPS

Does the job 1

The docs show it meets the test above, and nothing we read says otherwise.

ListingWhy
Formbricks D
Formbricks GmbH
count_responses, dashboards and get_chart_data return aggregated numbers, and every survey has a Summary view, but no time figure is given against the one-minute bar. source

Does the job, with a limit 10

It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.

ListingWhy
Alchemer F
Alchemer LLC
A surveyreport object exists alongside full paged response reads, but aggregate counts per option weren't confirmed in the pages read. source
Fillout E
Restly, Inc.
No aggregate results endpoint; a summary needs a full paged read at up to 150 submissions a page, which carries labels and types. source
Formstack E
Intellistack, LLC
GET submissions/count gives totals and a paged read gives the rest, but no per-option results endpoint exists. source
Google Forms API BB
Google LLC
No aggregate endpoint; a summary needs responses.list, up to 5,000 a page, plus forms.get to label answers. source
Jotform E
Jotform Inc.
Report endpoints exist under user and form, but per-option counts weren't shown; a full paged read with labelled answers is the documented route. source
Paperform C
Paperform Pty Ltd
No aggregate endpoint; a summary needs a full cursor-paged read at up to 100 a page plus the fields list for labels. source
SurveyMonkey D
SurveyMonkey Inc.
Rollup and trend endpoints return counts per survey, page and question in one call, but they need responses_read_detail, which is capped on Basic, and no timing is stated against the one-minute bar. source
Tally C
Tally BV
Analytics endpoints return metrics (visits, submissions, completion rate) and per-question drop-off, but not counts per choice; those need a full read of submissions. source
Typeform C
Typeform SL
MCP insights-public_aggregate returns counts, averages, sums and NPS for a field or dataset after insights-public_discover. Access is plan-dependent and no timing is stated against the one-minute bar. source
Wufoo D
SurveyMonkey Inc.
Reports and their widgets can be read through the API, but per-option counts depend on reports built in the web app; otherwise a full paged read of entries. source

What stops agents finishing

  • results endpoints on enterprise plans only

Around it

Before: forms.read-responses. After: docs.write-report, messaging.post.

Where this comes from

Weight 5 of 100 in Forms, surveys & structured intake: 1 of 25 accounts (Typeform MCP for reporting); SurveyMonkey and Typeform vendor pages make it a headline job

The same as data: /api/v1/use-cases/forms.summarise-results.json, or the MCP tool get_use_case with id forms.summarise-results. Other jobs in this category: /api/v1/niches?category=forms.

Draft, read 2026-11-15 from public docs and first-hand accounts, not yet reviewed by a person. A mark says what the docs show, not what a run measured.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.