TrueClicks

Perfmon fluctuation alerts

perfmon_fluctuation_alert

Read-only

Get the currently triggered perfmon FLUCTUATION alerts (a monitored metric moved too far vs the previous period) for one or more accounts as JSONL. Perfmon keeps no history, so this is the current state. Each line carries: Metric + ApiType, MetricType, AlertLevel (Increase/Decrease), Current + Previous value, ChangeValue (current − previous), PercentageChange (0..1 where 1 = 100%, e.g. 6.95 = 695%, vs previous), DefinitionLimit (the allowed fluctuation as a 0..1 fraction where 1 = 100%, e.g. 0.1 = 10%), Priority + PriorityNum, TimeRangeDays, and the target AccountIds/CampaignIds. Defaults to High + Critical only (pass minPriority to widen). Each alert's PerfmonId + PerfmonDefinitionMetricId identify the underlying per-campaign metric rows.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`accountIds`	No	Optional TrueClicks account ids to filter (the numeric Id field from the account listing, not the platform customer id). Omit or leave empty to return all accounts accessible by the connector.
`campaignIds`	No	Optional. Use this ONLY to focus on / analyze specific campaign(s). Pass the campaign id(s) you care about and only alerts scoped to those campaigns are returned (a single-campaign alert on any of them, or a campaign-group alert whose campaigns are all within your set). Account-level alerts and alerts touching other campaigns are excluded. Omit to get all alerts for the account(s).
`minPriority`	No	Minimum priority to include. Priority scale: 1=Insight, 2=Low, 3=Medium, 4=High, 5=Critical. Defaults to 4 (High) so only High + Critical are returned; pass 1 (Insight) to return all priorities.	High

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed2 schema fields changedSep 7, 2026

changedInput schema / properties / accountIds / description

Previous value: -"Optional account IDs to filter. Omit or leave empty to return all accounts accessible by the connector."New value: +"Optional TrueClicks account ids to filter (the numeric Id field from the account listing, not the platform customer id). Omit or leave empty to return all accounts accessible by the connector."

changedInput schema / properties / campaignIds / description

Previous value: -"Optional — use this ONLY to focus on / analyze specific campaign(s). Pass the campaign id(s) you care about and only alerts scoped to those campaigns are returned (a single-campaign alert on any of them, or a campaign-group alert whose campaigns are all within your set). Account-level alerts and alerts touching other campaigns are excluded. Omit to get all alerts for the account(s)."New value: +"Optional. Use this ONLY to focus on / analyze specific campaign(s). Pass the campaign id(s) you care about and only alerts scoped to those campaigns are returned (a single-campaign alert on any of them, or a campaign-group alert whose campaigns are all within your set). Account-level alerts and alerts touching other campaigns are excluded. Omit to get all alerts for the account(s)."

First observedSep 7, 2026

TDQS

A4/5.0

Behavior4/5

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

The readOnlyHint annotation already covers side-effect expectations, and the description adds useful context by stating that no history is kept and that the result is the current state. There is no contradiction between the description and annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is verbose, with a long enumeration of output fields and repeated emphasis on default priority behavior. The field list is valuable because there is no output schema, but the text could be tightened without losing important 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?

There is no output schema, so the description compensates by enumerating the fields carried in each JSONL line and explaining priority, filtering, and current-state semantics. It is reasonably complete for the tool's read-only nature.

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?

All parameters have detailed schema descriptions, including accountIds filtering, campaignIds scoping behavior, and minPriority values with defaults. The description largely repeats or restates this information rather than adding substantial new meaning, so the baseline of 3 is appropriate.

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 description clearly states the tool's purpose: getting currently triggered perfmon fluctuation alerts for one or more accounts as JSONL. It also distinguishes this from threshold alerts through the explicit 'FLUCTUATION' qualifier and the detailed alert semantics.

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 explains that the tool returns current state because perfmon keeps no history, and it specifies the default priority behavior. It does not explicitly contrast with the sibling perfmon_threshold_alert tool, but the fluctuation framing makes the intended use clear enough.

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

All TrueClicks tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0

Disambiguation4/5

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 Consistency4/5

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.

Tool Count4/5

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.

Completeness4/5

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.

Resources

Need Help?