Skip to main content
Glama

Quattr

render_analysis

Render a prior result — including a SYNTHESIS you composed across several queries — as an inline visual Quattr card. ALWAYS prefer this over generating your own HTML, images, or markdown tables — render_analysis produces native Quattr-styled output with built-in honesty chrome, deep-links, and responsive layout that your ad-hoc HTML cannot match.

component="Report" is the richest: a MetricCards summary strip + a comparison table in one card. component="DataTable" renders ranked/breakdown/comparison rows. component="MetricCards" renders stat cards. component="NoticeBanner" renders a capability-gap / no-data state.

EXPRESSIVENESS — what you can do with columns + sections: • sections — group rows into labeled, tone-colored buckets (e.g. "Keep" green, "Cut" red) with optional criteria descriptions. Use for any bucketed/segmented analysis. • type:"status" + toneMap — color-coded badge pills in cells (e.g. decision labels like "Keep — best CPA" in green, "Cut" in red, "Watch" in amber). • identitySubKey — a muted sub-line under each row's identity cell (e.g. intent category under keyword). • type:"delta" — ±change badges with automatic green/red coloring. • type:"bar" — inline horizontal bars for share/proportion columns. • prevKey — prior-period value as a muted sub-line in metric cells.

Pass the rows/cards you already have — no re-query. The honesty chrome (Observational basis, caveats, freshness) always renders as a footer; pass openInQuattrUrl to deep-link. Do NOT call this after a successful auto-rendered governed verb unless you are adding a valid cross-query synthesis or a materially different presentation the user requested. In a valid synthesis, preserve every measured, non-null source metric for every row; use null/— only when the source returned null or explicitly marked the metric not applicable. Never add decorative KPI cards when the table already answers the question. Market share/rates/ranks are non-additive: do not total them or derive a contribution from their sum.

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": {
      "component": "<component>",
      "title": "<title>"
    },
    "name": "render_analysis"
  }
}

Input Schema

NameRequiredDescriptionDefault
asOfNoFreshness date for the footer, e.g. "2026-06-15".
rowsNoDataTable / Report: the result rows (required for DataTable).
toneNoNoticeBanner tone: info (capability gap), error (unsupported), neutral (no data).
basisNoSet when the data is observational (renders the Observational chip).
cardsNoMetricCards / Report: the summary stat cards.
titleYesThe card title.
reasonNoNoticeBanner: an optional secondary reason line.
caveatsNoHonesty caveats to surface in the footer.
columnsNoRICH comparison columns — use INSTEAD of metricFields for synthesis tables that need a prior value under a cell, multiple typed delta columns (% and pts), inline bars, or color-coded status badges.
messageNoNoticeBanner: the main message (required for NoticeBanner).
tryVerbNoNoticeBanner: a suggested alternative verb to try instead.
sectionsNoGROUPED TABLE — sections with tone-colored headers, optional subtotals and criteria text. Use INSTEAD of rows for bucketed/segmented analyses (e.g. keep/cut/watch decisions). Each section has its own rows subset.
componentYesWhich palette component to render. "Report" = a synthesis: a MetricCards summary strip + a comparison table in one card (pass both `cards` and `rows`/`columns`).
rankByFieldNoDataTable: the metric the rows are sorted by (shown in the footer).
metricFieldsNoDataTable: simple metric columns (the rest if omitted). Include "delta"/"deltaPct" to get the gainers/losers split. Ignored when `columns` is given.
identityFieldNoDataTable: the label column (first non-numeric column if omitted).
identitySubKeyNoDataTable: a row key whose value renders as a muted sub-line under the identity cell (e.g. intent category under a keyword name).
openInQuattrUrlNoDeep-link URL for the "Open in Quattr" footer button.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=false, openWorldHint=false, destructiveHint=false, so the description carries real weight and does: it explains that honesty chrome (Observational basis, caveats, freshness) always renders as a footer, describes deep-linking via openInQuattrUrl, states that no re-query occurs, and imposes data-fidelity rules (preserve every non-null source metric, never total non-additive rates/ranks). The one unresolved point is what readOnlyHint=false means here, given the description reads as a purely presentational operation — an ambiguity the description does not address, though it does not directly contradict the annotation either.

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?

Purpose and the 'prefer this' rule are front-loaded in the first paragraph, and component semantics follow in a compact block. The EXPRESSIVENESS bullet list is where the text stretches — it is the longest section and overlaps substantially with the structured column schema, so some sentences do not fully earn their place. Given 18 parameters and four render modes, the overall length is defensible.

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 an 18-parameter tool with 100% schema description coverage and no output schema, the description supplies exactly the missing layer: component-selection logic, cross-component data rules, the non-additivity constraint, and the footer/deep-link behavior. An agent can assemble a correct call without additional context.

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 description coverage is 100%, so the baseline is 3 and the schema already documents every parameter. The description adds genuine selection guidance the schema omits (which component shape fits which analysis, that sections should be used INSTEAD of rows for bucketed analyses, that metricFields is ignored when columns is given), but several EXPRESSIVENESS bullets (identitySubKey, prevKey, status/toneMap, delta, bar) largely restate the schema's own param descriptions rather than extending them.

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?

The first sentence states a specific verb and resource — 'Render a prior result ... as an inline visual Quattr card' — and immediately scopes it against the alternatives an agent would otherwise reach for (own HTML, images, markdown tables). It also distinguishes itself from sibling presentation tools by naming what it produces ('native Quattr-styled output with built-in honesty chrome, deep-links, and responsive layout').

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?

It gives explicit when-to-use ('ALWAYS prefer this over generating your own HTML') and an explicit when-NOT clause ('Do NOT call this after a successful auto-rendered governed verb unless you are adding a valid cross-query synthesis'). It further routes component choice (Report vs DataTable vs MetricCards vs NoticeBanner) with a condition for each, so the agent knows which trigger selects which variant.

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