Paperform

Load trigger samples

load_trigger_samples

Fetch recent sample events for a workflow trigger from the connected account, so later steps can be written against real field paths. It reads real records through the connection (for a form's new-submission trigger, its latest submissions); nothing is changed in that account and no credits are spent. Confirm with the user before calling this.

Returns the samples as the trigger would emit them: { status, data: { items: [{ label, value }] }, descriptions? }. One can stand in for the trigger's event as run_workflow's payload. Pass workflow and node (the trigger's #id) to store one on that trigger of the draft as its example, as the editor's "Choose an example" does: the first item, or the one sample picks (0-based); when the account has none (a brand-new form, say), the trigger's example as the editor builds it, else its static one. The answer's example also carries checks: warnings on paths other steps read from this trigger that the stored example does not offer. The trigger must run this app, trigger and connection; that is checked before anything is fetched. The answer then carries example: { stored, note, workflow_version? }, and the draft's version changes, so fetch #source again (or pass workflow_version as edit_source's expected) before the next edit. edit_source and create already load a sample for a trigger they add or change, so call this to pick another item, or when that load found none.

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": {
      "app": "<app>",
      "trigger": "<trigger>",
      "connection": "<connection>"
    },
    "name": "load_trigger_samples"
  }
}

Input Schema

Name	Required	Description
`app`	Yes	The app id, exactly as list({ type: "app" }) returned it.
`node`	No	With workflow: the #id of the trigger or step in the workflow's draft the example is for.
`input`	No	The parameter values chosen so far, key → value (plain values, not the source forms). Later parameters often depend on earlier ones.
`sample`	No	With workflow and node: the 0-based index of the item to store. Defaults to 0, the first.
`trigger`	Yes	A trigger key, from fetch on the app.
`workflow`	No	Optional: a workflow id, as list or fetch returned it, to store a sample on one of its steps as that step's example. Needs node too, and write access to the workflow.
`connection`	Yes	A connection id for this app, from list({ type: "connection" }) or fetch on the app.

Output Schema

Name	Required	Description	Default
`data`	No
`example`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 6, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Goes well beyond the annotations: no credits spent, nothing changed in the connected account, a pre-flight validation of app/trigger/connection, a side effect on the draft version with remediation ('fetch #source again'), and warnings emitted about paths other steps read that the example does not offer. This is consistent with readOnlyHint=false given the disclosed draft mutation.

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

Conciseness3/5

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

Front-loaded with purpose, but the long middle sentence about storing an example (editor analogy, index, fallback chain, checks) is hard to parse and partially restates the schema. Several clauses could be split or trimmed without losing information.

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 7-parameter tool with nested objects, the description covers prerequisites, side effects, version staleness, follow-up calls, and guidance about which sibling handles which case. Return values are explained even though an output schema exists, which is redundant but not harmful.

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 already 100%, so the baseline is 3, but the description adds real semantics: workflow+node means store the sample as that step's example, sample is the 0-based pick defaulting to 0, and there is a fallback chain when the account has no records (editor-built example, else static). The prose is dense enough that extracting these interactions takes effort.

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 — 'Fetch recent sample events for a workflow trigger from the connected account' — and clarifies the payoff ('so later steps can be written against real field paths'). It also separates itself from siblings by noting edit_source and create already load a sample, and that a sample can stand in as run_workflow's payload.

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?

Explicit when-to-use ('call this to pick another item, or when that load found none'), explicit exclusions (edit_source and create already load one), a confirmation gate ('Confirm with the user before calling this'), and a stated precondition ('The trigger must run this app, trigger and connection; that is checked before anything is fetched').

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

All Paperform 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?