Skip to main content
Glama

add_widget

Add a DATA widget (table, chart, KPI…) to a report using plain language, e.g. "add a monthly Google Ads performance table", "add a KPI card of GA4 conversions", or BLENDED across every paid channel: "leads by month across all channels", "blended cost per lead by calendar week", "a table comparing all paid channels with a total" (needs two or more paid ad accounts; rates are recomputed from pooled totals, never averaged). It maps the request to the report's connected data and adds the widget — or, if the data isn't connected or we don't support that metric yet, tells you why. Granularity words (daily, weekly, monthly, by month, per week; täglich, wöchentlich, monatlich, pro Monat) set a chart's time scale deterministically; a period ("last 12 months") is never read as one. GA4 visits by channel PER MONTH ("sessions by channel per month for the last 12 months") is the GA4 table "Channel × Month": one row per channel, one column per calendar month, one metric, optional totals and shading. PLACEMENT: goes at the end of the report unless position says otherwise — start, end, before or after a widget, or section_start / section_end of a section (anchorId = that widget's or section's id, from get_report; after a section = after everything in it) — or the instruction states it by naming an existing widget or section ("in the Google Ads section, right after the Top campaigns table"). A stated placement that names no widget, or a title two widgets share, keeps the end and the preview says so. The preview shows where the widget will go. The instruction is read by AI: the preview's aiCost says who pays for it (the workspace's own AI key, billed by its provider, or CrunchJunkie's at no charge). Requires MCP write actions; without confirm:true it returns a preview. For a free-text block you write yourself, call add_text_widget.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
confirmNoSet true to add it. Omit for a preview of what will be interpreted and added. With confirm:true, also pass the preview's previewToken.
anchorIdNoWith position before, after, section_start or section_end: the id of the widget or section (from get_report). After a section = after everything in it.
positionNoWhere the widget goes (default end, or what the instruction states): start, end, before / after a widget, section_start / section_end of a section. All but start and end need anchorId. Wins over a placement in the instruction.
reportIdYesReport id (from list_reports).
instructionYesWhat widget to add, in plain language. It may say where ("right after the Top campaigns table", "at the end of the SEO section") when it names an existing widget or section.
previewTokenNoWith confirm:true: the previewToken from this tool's preview (valid 15 minutes, once, for exactly the previewed arguments).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

With annotations only declaring readOnlyHint=false and destructiveHint=false, the description adds substantial context: it requires MCP write actions, returns a preview without confirm:true, describes the single-use 15-minute previewToken, discloses aiCost billing responsibility, and states fallback behavior when data isn't connected. This is rich disclosure well beyond the annotations.

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 example, then structured with a PLACEMENT: marker and trailing fallback/alternative notes. It is dense and long, with some repetition of placement logic that also lives in the schema, but nearly every clause carries invocation-relevant information.

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

Completeness4/5

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

For a complex 6-parameter mutation tool with no output schema, it covers interpretation, placement, preview/token flow, billing, and error/fallback behavior. The only minor gap is that it doesn't describe the shape of a successful (non-preview) result, e.g. the created widget id.

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 meaningfully extends the schema: granularity keywords (daily/weekly/monthly, incl. German) set chart time scale, a period is never read as one granularity, and placement/anchor semantics are elaborated. It adds genuine semantic detail over the parameter docs.

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 (add) and resource (DATA widget: table, chart, KPI) to a report, and explicitly distinguishes itself from the sibling add_text_widget for free-text blocks. An agent can tell it apart from related tools without opening any schema.

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?

Gives explicit when-to-use alongside the add_text_widget alternative, explains the confirm:true / preview split, the placement defaults and overrides, and the blended-channel precondition (two or more paid ad accounts). Routing conditions and prerequisites are stated, not inferred.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources