ms_ads_report_columnsGet the selectable columns for a given Microsoft Ads report as CSV (one per row). These column names are the valid entries for the report query's 'columns' argument.
| Name | Required | Description | Default |
|---|---|---|---|
| report | Yes | Name of a Microsoft Ads report (one of the available report names). |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already indicates no side effects. The description adds the concrete output format (CSV, one column name per row), which helps set expectations. No behavioral contradictions exist.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise, with no redundant wording. It communicates the resource, output format, and downstream usage in one short paragraph.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple single-parameter read-only tool, the description is complete: it states what is returned, in what format, and how the result should be used. No output schema is provided, but the CSV format is explicitly described.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema property description fully explains that 'report' is the name of a Microsoft Ads report and one of the available report names, linking conceptually to the reports list tool. This adds enough context beyond the raw parameter name.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets selectable columns for a Microsoft Ads report, specifies CSV output format (one per row), and explains their purpose as valid entries for the report query's 'columns' argument. This distinguishes it from sibling tools like ms_ads_reports_list and ms_ads_execute_report_query.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool should be used to discover valid column names before constructing a report query's 'columns' argument. It does not explicitly mention alternatives or when not to use it, but the reference to the query's columns argument gives clear practical guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct purposes, but the audit and report tools (e.g., audit_rule_output_table vs audit_rule_output_table_historical vs audit_rule_result vs audit_rule_result_campaign) are closely related and rely on detailed descriptions to differentiate.
Naming is generally consistent with snake_case and domain-prefixed groups (google_ads_*, ms_ads_*, perfmon_*), though a few tools are bare nouns (account, task, user) rather than verb-led, which slightly deviates from the dominant pattern.
23 tools is on the higher end but justified for a platform covering multiple ad platforms, audit reports, alerts, and user management; it remains navigable with clear groupings.
The tool set comprehensively covers account enumeration, audit results, report execution for major ad platforms, perfmon alerts, pacing targets, tasks, and users. Minor gaps exist (e.g., no create/update/modify operations), but the core analytics and monitoring surface is well covered.