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

Annotations already declare read-only, non-destructive, closed-world, so the description is free to add operational context — and it does: newest-first ordering, a 7-day default window, a data-freshness caveat ('a new session appears a few minutes after its events'), and cursor pagination. It stops short of describing result shape or edge cases like empty windows, but the behaviorally important traits are covered.

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?

Front-loaded with the core action and the default scope, then the returned fields, then filter provenance and freshness. The field enumeration ('channel, source / medium, campaign, landing page, country, device and more') is a bit list-heavy but earns its place by telling the agent what comes back.

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?

With an output schema present the description needn't explain return values, and it covers defaults, date limits, pagination, and ingestion latency. The remaining gap is sibling disambiguation — search_sessions vs list_sessions vs query_sessions is left ambiguous in a crowded family of session tools.

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 schema already carries the per-parameter documentation and the baseline would be 3. The description adds genuine meaning the schema does not: filters accept the values of a run_report row, and 'paged with next_cursor' ties the cursor param to the pagination cycle. It doesn't elaborate on limit/date interplay, so not a 5.

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 specific verb and resource ('Lists the sessions that started in a date range') plus the returned payload (report values, pageviews, events, landing URL, referrer) and sort order. It does not, however, distinguish itself from the closely related siblings list_sessions and query_sessions, which an agent would need to choose between.

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 implied rather than stated: 'The filters take the values of a run_report row' hints at how to pick filter values, and the 7-day default plus 400-day cap scope the call. There is no explicit when-to-use/when-not or routing to list_sessions/query_sessions for alternative access patterns.

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