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

Annotations already cover read-only, idempotent and non-destructive behavior, yet the description still adds real value: Google's 30-day retention cap, oldest-first ordering, grouping by day, and the actor taxonomy (person, script, automated rule, auto-applied recommendation). It does not mention response size or pagination, which for a potentially large day-grouped history is the remaining gap.

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?

Two dense sentences, front-loaded with scope and ending with the retention constraint that qualifies everything before it. The 'Unlimited plan.' fragment is a little abrupt but carries real gating information, so little is wasted.

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 read-only tool with rich annotations, full schema coverage and no output schema, the description supplies what structured fields cannot: the retention window, ordering, grouping, actor types, and exactly which values accompany each day. An agent can call this correctly and predict the shape of the result.

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 coverage is 100%, so the baseline is 3, and the description earns more by explaining what the comparison window actually produces ('the account spend and conversions in the days before and after') and by reinforcing the 30-day ceiling that the `days` maximum encodes. It still doesn't tie its wording explicitly to the `login_customer_id` access path.

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?

States a precise verb+resource ('every change made in the account') plus ordering, grouping and payload contents. This clearly separates it from siblings like export_history or did_it_work, which are about exporting or validating outcomes rather than reading the audit trail.

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: the 'Unlimited plan' note and the 30-day retention statement tell the agent about a prerequisite and a hard limit, but nothing says when to pick this over export_history or why_not_upgrade. No explicit when-not or alternative routing is given.

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