ZeroWidth

Generate a Caliper dataset from a flow (spends credit)

caliper_datasets_generate

Creates a NEW dataset of model-written items — Q&A by default, or scripted sequences / simulated people via shape — pass flowId and the generator reads the flow's prompt, mode, and schema to write realistic cases for THAT flow; description adds guidance (or stands alone when there's no flow). Use this when the user wants test cases fast and has none; prefer caliper_datasets_create with hand-written items when real scenarios are already in hand (Compass pages, a transcript). This SPENDS workspace inference credit (one generator call), so it sits behind the approval gate: say so and expect needs_confirmation. Returns the dataset summary; read the items with caliper_datasets_get and tell the user to review them before trusting an eval built on them.

Input Schema

Name	Required	Description
`count`	No	Items to generate, 1-50. Default 10.
`shape`	No	What each generated item is: `qa` (one input, the default), `sequence` (2-6 scripted user turns the model answers one at a time, with expectedResponse + expectedBehavior), or `simulated` (a person Caliper plays adaptively: goal, persona, disposition, expectedBehavior). outputsMode applies to `qa` only.
`title`	Yes	Dataset name.
`flowId`	No	Workbench flow to generate cases for (from workbench_flows_list). Required unless description is given.
`presetId`	No	Framing preset. Default `blank`; the others bias every item toward that attack class.
`workspace`	No	Workspace slug. Personal tokens with no default workspace MUST pass this; tokens with a default can override per call. Ignored for workspace API keys.
`approvalId`	No	Approval id from a prior needs_confirmation response. Omit on the first call.
`visibility`	No	Who can see it: PRIVATE (only the user), WORKSPACE (every member, the default), or SHARED (specific people, granted afterwards). Say 'make it private' → PRIVATE.
`description`	No	What the target system does / what to cover. Required (≥10 chars) when flowId is omitted; optional guidance otherwise.
`disposition`	No	With shape `simulated`: how every generated person behaves — a preset id (genuine, pressure, confused, impatient, vague, non-native) or free text. Omit to let the generator vary it from person to person.
`outputsMode`	No	What each generated item carries beyond the input: `expected` (golden answers — eval-ready, the default), `none` (inputs only — for a spec others fill in), `captured` (sample answers to rate in a review).
`expectedStyle`	No	With outputsMode `expected`: `verbatim` literal reference answers (default) or `conditions` — what a correct answer must do, when there's no single right wording.
`datasetDescription`	No	Description stored on the dataset.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 7, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only cover readOnly/destructive/openWorld; the description adds the crucial cost trait ('SPENDS workspace inference credit (one generator call)'), the approval-gate behavior ('expect needs_confirmation'), and the required follow-up read via caliper_datasets_get. These are non-obvious side effects an agent must communicate to the user.

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?

Front-loaded with the core action and credit warning, and every clause carries information. It is fairly dense across multiple em-dash clauses, so a small amount of tightening is possible, but nothing reads as filler.

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 13-param, no-output-schema mutation with spend, the description covers what it returns ('dataset summary'), the follow-up read, cost, and approval flow — the info an agent needs. Nothing material is missing given the schema carries all parameter detail.

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 baseline is 3, but the description adds real meaning: it explains the flowId/description contract (description 'stands alone when there's no flow'), the generator's behavior of reading the flow's prompt/mode/schema, and the default shape. It does not add much for the enum params beyond the schema.

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+resource ('Creates a NEW dataset of model-written items') and immediately distinguishes the output variants (Q&A, scripted sequences, simulated people via `shape`). It also names the sibling it is not (caliper_datasets_create) so an agent can route correctly without opening schemas.

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 ('when the user wants test cases fast and has none') and when-not ('prefer caliper_datasets_create with hand-written items when real scenarios are already in hand — Compass pages, a transcript'). It further flags the approval-gate path and the expected needs_confirmation response, leaving little to inference.

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

All ZeroWidth 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?