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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the trailing 'Read-only.' largely restates structured data rather than adding to it. The enumerated checks do reveal that the tool inspects live tag firing and cross-reads the GA4 link, but nothing is said about latency, cost, or permission requirements for those cross-service reads.

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?

Purpose and coverage list are front-loaded in a single dense sentence with an em-dash aside, and nothing is padded. The trailing 'Tools revision: d80f65c0.' is build metadata that consumes space without helping selection, a minor blemish.

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?

An output schema exists, so return values need not be described, and the audit checklist is thorough enough to convey scope. Against that, five parameters with zero schema coverage and no description-level explanation leaves the agent guessing about lookback windows, detail level and output rendering.

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?

Schema description coverage is 0% across five parameters (customer_id, days, detail, render, max_findings), and the description supplies no meaning for any of them. In particular the two enums, the default 30-day lookback, and the cap on findings are left entirely unexplained, so the agent must infer behavior from bare titles and defaults.

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 gives a specific verb-plus-resource ('Check whether conversion tracking can be trusted') and enumerates the exact dimensions audited: primary actions, enhanced conversions, attribution model, values, duplicate counting, GA4 link, consent mode, tag firing. That scope distinguishes it in practice from siblings like full_audit, bidding_audit and explain_conversion_gap, though none of those alternatives are named.

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?

Usage is only implied by the framing 'the measurement every other number in the account rests on', which suggests running it before trusting performance data. There is no explicit when-to-use statement, no prerequisites (account access, GA4 linkage), and no routing to the closely related siblings such as explain_conversion_gap when a discrepancy is already known.

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