Oviond

Update data widget

update_data_widget

Update a DATA widget — its name, datasource, data view, metrics, dimensions, filters, advanced settings, chart type, date range, sort and row limit. Applies the report builder's rules: a new datasource or data view clears the selections below it and re-applies defaults, per-metric renames and formats are kept, the combination is validated, and the series is re-fetched with the new config. Discover ids with datasources → describe_datasource. The re-fetch runs in the background — call get_widget_data with this id to read the new numbers.

Input Schema

TableJSON Schema

Name	Required	Description
`id`	Yes	Widget ID (from list_widgets).
`name`	No	Display name. Omit to use the generated one ("Clicks & Impressions by Date")
`chart`	No	Chart type: table, score (KPI), area, line, bar, column, pie, donut, funnel, or map. 'score' shows a single value, so it takes exactly one metric
`filters`	No	Row filters. Every row needs a field, an operator and a value
`metrics`	No	Metrics to display, e.g. [{ value: "clicks" }] — ids from describe_datasource. Must belong to the chosen data view. Only `value` is required; the server fills the rest
`sort_by`	No	Metric or dimension id to sort rows by. Defaults to the first dimension
`advanced`	No	Datasource-specific settings (Meta attribution, SEM Rush region, Mailchimp audience…). Several datasources require keys here — describe_datasource lists them per data view. Merges with existing settings
`currency`	No	Per-widget currency code override; falls back to the client currency
`data_view`	No	Datasource data view (from describe_datasource), e.g. ACCOUNT. Changing it clears metrics and dimensions
`row_limit`	No	Rows to keep (default 'all')
`date_range`	No	Per-widget date range (overrides the report range) — also set show_custom_date_range
`dimensions`	No	Breakdown dimensions, e.g. [{ value: "DATE" }] — ids from describe_datasource. A widget needs at least one; a dimension flagged `single` must be the only one
`sort_order`	No	Sort direction (default 'asc')
`datasource_id`	No	Datasource alias (from datasources), e.g. gadw. Changing it clears the data view, metrics, dimensions, filters and advanced settings, then applies that datasource's defaults. A datasource the client has not connected renders demo data until the connection is made — connected_datasources shows what is connected. The internal sources take no metrics/dimensions and are configured through `advanced` instead: 'CUSTOM_DATA' (Static Value — advanced.value), 'GOALS' (advanced.goal_id from list_goals), 'CUSTOM_IMPORT' (advanced.custom_data_id from list_custom_data), 'CALCULATION' (a calculated metric id as the single metric)
`show_custom_date_range`	No	Use the widget date_range instead of the report range

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	No	The data widget as saved, with the builder's rules applied — cleared selections, re-applied defaults and the regenerated name. When the selection changed the series is re-fetching in the background; read it with get_widget_data.
`success`	Yes	True when the call succeeded. A failure comes back as an error result instead.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 18, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "data": {
+      "additionalProperties": {},
+      "description": "The data widget as saved, with the builder's rules applied — cleared selections, re-applied defaults and the regenerated name. When the selection changed the series is re-fetching in the background; read it with get_widget_data.",
+      "type": "object"
+    },
+    "success": {
+      "description": "True when the call succeeded. A failure comes back as an error result instead.",
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "success"
+  ],
+  "type": "object"
+}

First observedSep 18, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Discloses side effects beyond annotations: changing datasource/data_view clears dependent selections and re-applies defaults, validates the combination, and re-fetches the series in the background. Also tells the agent to call get_widget_data to read new numbers. No contradiction with readOnlyHint/destructiveHint.

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?

Four dense sentences, each earning its place: field scope, update semantics, id discovery, and post-update fetch. Front-loaded with the field list; no 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 15-param mutation tool with nested objects, the description plus schema fully covers prerequisites, behavior, and how to observe results. Output schema exists, so return-value documentation isn't needed; nothing critical is 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?

Though schema coverage is 100%, the description adds cross-parameter semantics: which changes cascade (datasource/data_view), which settings are preserved (per-metric renames/formats), and where to discover ids (datasources → describe_datasource). It also highlights that internal datasources are configured via advanced instead of metrics/dimensions.

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 (Update) + resource (DATA widget) and enumerates the configurable fields (datasource, data view, metrics, dimensions, filters, chart type, etc.). The capitalized 'DATA widget' distinguishes it from siblings like update_button_widget, update_custom_data_widget, and update_static_value_widget.

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?

Gives clear operational context: it's for updating an existing widget, with a discovery flow (datasources → describe_datasource) and a follow-up call (get_widget_data). It does not explicitly name alternatives like add_data_widget for creation, so it is clear context rather than explicit when-not guidance.

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

All Oviond 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?