asksteps

asksteps: turn a described form into an openable draft

asksteps_create_draft

Turns a form you have designed with the user into a draft and returns a link. Opening the link shows the form in the asksteps builder, where the user can change it and save it — no account is needed to look at it. Use this once you and the user agree on what the form should ask; it is the step that turns the conversation into something they can actually use. It does NOT write into anyone's account: a human always saves it. Give the returned url to the user verbatim. For digitising an existing PDF, do not rebuild it here — the analysis only shows you part of a large form. Point the user at the PDF import in the product instead. If the draft is rejected, the note says exactly what to fix; correct it and call again.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`spec`	Yes	The form: a name and its steps with their fields.

Output Schema

TableJSON Schema

Name	Required	Description
`url`	Yes	The link to open the draft in asksteps. Give this to the user verbatim — it is the whole point of the tool. 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.
`status`	Yes	Outcome. One of: "created", "invalid_spec" (the draft was rejected — see note).
`stepCount`	No	Number of steps and fields the draft ended up with, so you can tell the user what they will see.
`fieldCount`	No	Total number of fields across all steps.
`validForDays`	No	How many days the link stays valid.

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the annotations, the description adds valuable behavioral context: the link opens in the builder, no account is needed to view it, it does not write into anyone's account, a human always saves it, and the returned URL must be given verbatim. It also explains the rejection behavior and what to do after a failed call.

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?

The description is front-loaded with the core purpose and then provides dense, non-redundant guidance on usage, behavioral implications, failure handling, and alternatives. Every sentence adds actionable information without fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of the nested spec schema and the presence of an output schema, the description covers all necessary context: when to call, what happens after the call, how to handle the returned link, rejection recovery, and the crucial no-account side effect. Nothing important is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the spec parameter is thoroughly documented in the input schema. The tool description adds context about the workflow but does not need to repeat parameter details, so the baseline score of 3 is appropriate.

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 first sentence states a specific action ('Turns a form you have designed with the user into a draft') and a concrete output ('returns a link'). It clearly distinguishes this tool from siblings like asksteps_create_form by emphasizing the draft-and-human-save workflow rather than direct account writes.

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 explicitly says when to use it ('once you and the user agree on what the form should ask'), gives a clear when-not case ('For digitising an existing PDF, do not rebuild it here'), and names the alternative ('Point the user at the PDF import in the product instead'). It also covers the rejection retry flow.

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?