Skip to main content
Glama

Report Audit

report_audit
Read-only

Audit a Data Studio report for silently broken or viewer-different pages, filters, blends, and datasources, and optionally open pages live to flag rendering errors and invalid configs.

Instructions

Find everything that silently breaks the report or differs for viewers.

Saved rules check every page, filter, blend and attached datasource: filters on ad-hoc formulas ('New field'), fields missing or disabled in their datasource, filters bound where their fields do not exist (silently not applied), detached or dangling datasources/filters/blends, broken datasource field formulas (including columns dropped by a source schema change), unpublished datasource drafts and viewer-credential datasources, chart-local formulas, unused filters and blends. With live=true it also opens each page in the viewer and reports components that render with an error or an invalid configuration, then returns to the starting page (page_ids limits the live pass to those pages). Each finding has rule, severity, meaning, fix and location. healthy=false means at least one error. Read-only; needs the tab in View mode for the live pass.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "report_audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
liveNo
page_idsNo
report_idNo
live_timeout_secondsNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, and the description reinforces this while adding genuinely new context: the live pass navigates the viewer through each page and then returns to the starting page, and it requires View mode. That side-effect disclosure is valuable beyond the annotation. It stops short of explaining cost/latency of the live pass or what live_timeout_seconds governs.

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?

The headline problem statement is front-loaded, followed by what is checked, then the live-pass behavior, then the finding shape and pass/fail flag. The long middle enumeration is dense but each item names a distinct failure mode rather than padding. Minor redundancy in restating read-only after the annotation.

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 diagnostic tool with an output schema, the description covers the important gaps: what classes of problems are detected, the shape of each finding (rule, severity, meaning, fix, location), the healthy flag semantics, and the View mode prerequisite for the live pass. Return-value details are correctly left to the output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the burden. It explains live and page_ids well (live pass enablement and page scoping) and report_id is self-evident from the tool name, but live_timeout_seconds is never mentioned, leaving a quarter of the parameters without semantics anywhere.

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 opening line states a specific verb and scope ('Find everything that silently breaks the report or differs for viewers') and the enumeration of checks (page, filter, blend, attached datasource, ad-hoc formulas, dangling references) makes the domain unmistakable. No sibling tool (report_inspect, report_filters, blend_validate) covers this same 'silently broken report' territory, so an agent can route here without opening a schema.

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?

It gives clear operating conditions: live=true triggers the viewer pass, page_ids scopes that pass, healthy=false signals at least one error, and the tab must be in View mode. What is missing is any explicit when-not or named alternative (e.g. when a non-live static check is preferable), so the agent must infer the exclusion.

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

Deploy Server

Other Tools