Attribution check

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

The description aligns with the readOnlyHint annotation (no destructive actions implied) and adds useful behavioral context beyond the annotation by explaining what the tool diagnoses (consent gaps, attribution differences, missing configuration). It does not describe side effects, which is appropriate given the read-only nature, and there is no contradiction.

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 structure is reasonably organized with a summary line and a detail line, but it contains redundancy: 'Compare Ads-reported conversions vs GA4 — find tracking discrepancies' essentially restates 'Checks whether conversions reported by Google Ads match what GA4 records'. This repetition could be trimmed without losing information, though the parameter notes are clear and well-placed.

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?

Given that an output schema is present, it is not necessary to describe return values. The description covers the core behavior, parameter defaults, and date handling, which is sufficient for an agent to invoke the tool correctly. Minor gaps remain around the exact identifiers (customer_id/property_id) and any assumptions about required permissions, but these do not materially impede use.

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 has zero parameter descriptions, but the description compensates for the non-obvious parameters: it explains conversion_events (optional list of GA4 events, null defaults to aggregate comparison) and the date range format with the 30-day fallback. However, customer_id and property_id are left undefined—their meaning (likely Google Ads customer ID and GA4 property ID) is only inferred from the tool name and context, so the compensation is incomplete.

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's specific function: comparing Ads-reported conversions against GA4 data and finding tracking discrepancies. It goes beyond generic verbs like 'check' to name concrete diagnostic outputs (GDPR consent gaps, attribution model differences, missing conversion event configuration), which distinguishes it from the many reporting tools in the sibling list.

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 provides some practical usage details, such as optional conversion_events filtering, date format expectations, and the default 30-day window when dates are empty. However, it does not explicitly state when to prefer this tool over closely related siblings like audit_event_coverage, validate_tracking, or analyze_campaign_conversions, nor does it mention what scenarios are out of scope.

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