asksteps

asksteps: create a branching funnel

asksteps_create_funnel

Creates a conversational funnel in the connected asksteps account: one question at a time, where each answer decides what comes next. Requires "forms:write". Use this instead of asksteps_create_form when answers should lead to DIFFERENT follow-up questions, or when someone should be able to be ruled out part-way through. Give every question a short ref ("budget", "contact") and point each answer's target at another ref, at "next", at "success" or at "dismiss". The first question in the list is where the funnel starts. It is NOT published; publishing is a separate step.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`spec`	Yes	The funnel: a name and its questions with their answers and targets.

Output Schema

TableJSON Schema

Name	Required	Description
`url`	No	Link that opens the form in the asksteps studio. Give it to the user so they can look at the result. Absolute when this deployment knows its public base URL, otherwise a site-relative path; never invent the domain part.
`note`	Yes	One sentence for the user. On rejection it says exactly what to fix.
`formId`	No	The id of the form. Keep it — it is how you read or change the form later.
`status`	Yes	Outcome. One of: "created", "updated", "not_connected", "not_found", "invalid_spec" (the structure was rejected — the note says exactly what to fix), "not_editable" (this form cannot be written from a spec), "unavailable", "error". Authorisation can also refuse before the tool runs: "plan_required" (the account's plan does not include agent access), "not_enabled" (the account owner has not switched agent access on), "owner_required" (only the account owner may do this), "mandate_required" (the owner has not granted a mandate for this). The note then says what the user has to do.
`stepCount`	No	Number of steps the form ended up with.
`fieldCount`	No	Total number of fields across all steps.

TDQS

A4.6/5.0

Behavior4/5

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

Annotations are all negative hints (not read-only, not idempotent, not open-world, not destructive), so they reveal little beyond 'this is a mutation.' The description adds genuinely useful behavioral context: the required scope "forms:write" and the crucial lifecycle fact that the funnel is created but not published — publishing requires a separate step. This prevents the agent from wrongly assuming the funnel goes live. No contradiction with annotations. It stops short of a 5 by not covering edge behaviors like duplicate-name handling or whether the result is a draft.

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?

Six sentences, each earning its place: purpose, required scope, sibling routing, ref/target construction model, start-point rule, and publication state. The core definition is front-loaded and there is zero filler or repetition of schema content. It is dense but structured so an agent can parse it quickly.

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?

Given the complexity — a deeply nested spec with nodes, answers, targets, screens, and settings — the description covers the semantic gaps the schema cannot: branching direction, target vocabulary, start point, auth scope, and the not-published state. The output schema covers return values, and the 100% schema coverage covers field details. Minor gaps keep it from 5: it does not cross-reference the publish sibling tool by name, nor clarify that existing funnels should be edited via asksteps_update_funnel.

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 per-field burden is already carried by the schema — baseline 3. The description adds above-baseline value by explaining the wiring model that the schema's individual field docs don't convey: refs are short jump targets, answer targets can be 'next'/'success'/'dismiss'/another ref, and 'the first question in the list is where the funnel starts.' This explains the relationships between parameters rather than just their types.

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: 'Creates a conversational funnel in the connected asksteps account', then defines the core mechanism ('one question at a time, where each answer decides what comes next'). It explicitly differentiates from the closest sibling, asksteps_create_form, by naming the distinguishing conditions (different follow-up questions, ruling someone out part-way). An agent can reliably tell this tool apart 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?

The description gives explicit when-to-use guidance: 'Use this instead of asksteps_create_form when answers should lead to DIFFERENT follow-up questions, or when someone should be able to be ruled out part-way through.' This names the alternative, the selection conditions, and — by implication — when not to use this tool. It also sets expectations for the downstream workflow ('NOT published; publishing is a separate step').

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

All asksteps tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0

Disambiguation4/5

Tools are mostly distinct with clear ownership of each resource and action, and descriptions explicitly contrast sibling pairs (analyze_pdf vs import_pdf, create_form vs create_funnel, publish_form vs update_publication, change_plan vs start_checkout). However, an agent skimming names alone could misselect between the four creation tools or the two PDF tools without reading the descriptions carefully.

Naming Consistency5/5

Every tool follows the asksteps_<verb>_<noun> pattern perfectly, with uniform verbs like get_, list_, create_, and update_. The only slight deviation is create_from_template, but even that stays predictable and readable within the convention.

Tool Count3/5

At 24 tools, this sits at the heavy end of the 16-25 borderline range. The broad domain (form/funnel building, publishing, PDF import, billing, stats, leads) justifies most of them and there is no obvious redundancy, but the sheer volume makes navigation harder than a tighter set.

Completeness4/5

The core form and funnel lifecycle is well covered: multiple creation paths, read, full replacement update, delete with confirmation, publish/unpublish, stats, and leads export. Billing covers first purchase, plan changes, and quota checks. Minor gaps exist — no dedicated subdomain listing tool, no funnel-specific stats, and no programmatic PDF field mapping — but these are explicitly documented as human steps, so agents can work around them.

Resources

Need Help?