Skip to main content
Glama
Sign In

Youform

by io.github.mkmaker
OverviewDiscussionsAdmin

Add block

add-block-tool

Add a new block of the given type to a form's draft. The block is created with sensible defaults — use update-block-tool afterwards to set its title, options, and settings. Returns the new block including its id. To add an ENDING page (thank-you / result screen where the form finishes) pass type "text" with is_thank_you true: it is appended after the last question and flagged is_last. Outcome quizzes need one ending page per outcome; a plain statement is NOT an ending — respondents would click through it into the next page.

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": {
      "form_slug": "<form_slug>",
      "type": "<type>"
    },
    "name": "add-block-tool"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeYesThe block type — must be an exact key from list-block-types-tool (e.g. input, textarea, email, phone, radio, dropdown, checkbox, star_rating).
group_idNoOptional multi-question page id to append this question inside that group. Create the group first with type group.
form_slugYesThe form's slug.
is_thank_youNoTrue to create an ending page (the form finishes here). Use type "text". Ignored for after_block_id; endings always go last.
after_block_idNoOptional id of the block to insert after. Omit to append before the thank-you screen.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare the non-destructive, non-open-world write profile; the description adds real behavioral context beyond that — blocks are created with defaults, the call returns the new block including its id, endings are appended last and flagged is_last, and a plain statement will not terminate the form. It stops short of describing ordering/interleaving errors or any limits on block counts, but the mutation semantics are well covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core action and the update-block-tool handoff are front-loaded in the first two sentences, with the edge-case ending-page rule following. It is dense but every sentence carries distinct information; the ending-page paragraph is the longest and could be tightened slightly without losing substance.

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?

For a five-parameter mutation tool with no annotated permissions detail and no output schema, the description supplies the return value, the defaults behavior, the follow-up workflow, and the non-obvious ending-page semantics including the is_last flag. Nothing an agent needs to call this correctly appears to be 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 100%, so baseline is 3, but the description adds meaning the schema does not carry: is_thank_you only makes sense combined with type "text", endings always go last regardless of after_block_id, and outcome quizzes need one ending per outcome. That is genuine semantic guidance rather than restatement.

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 ('Add a new block of the given type to a form's draft') and immediately distinguishes itself from the sibling update-block-tool, which handles the property-setting this tool does not. An agent can tell what this tool does and what it doesn't 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit routing is given for the follow-up step ('use update-block-tool afterwards to set its title, options, and settings') and for the ending-page case, plus a prerequisite for group_id in the schema ('create the group first with type group'). It does not say when to prefer create-form-with-questions-tool over this tool, which is the one remaining ambiguity among the siblings.

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

All Youform toolsInspect
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