List Events

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

Annotations already declare readOnlyHint/idempotentHint, so the safety profile is covered. The description adds genuinely non-obvious behavior: a 2-year retention window and the exact token permissions required, including the delegate-to-contact scope. It stops short of describing return shape or pagination semantics.

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 the retention caveat are front-loaded, which is good. The embedded permission block with a fenced code snippet is somewhat bulky, but each element (purpose, retention, auth) is distinct information rather than repetition.

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 nine parameters, no output schema, and openWorldHint, the description covers auth and retention but omits what an event record contains and how the all_pages/max_items continuation state surfaces in results. Adequate but leaves real gaps for a paginated list tool.

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 100%, so all nine parameters (page, per_page, all_pages, max_items, date filters, media_id, visitor_key) are already documented in the schema, including the per-request quota note on all_pages. The description adds nothing about parameter semantics, so the baseline 3 applies.

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 clear verb and resource ('Retrieve a list of events'), so an agent knows this is a list operation. However, it never disambiguates from the sibling get_event, nor clarifies what kind of 'events' these are (analytics/visitor events), which matters in a large sibling set full of list_* tools.

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 gives no when-to-use guidance, no exclusions, and does not mention any alternative such as get_event or the visitor/media-scoped list tools. The only conditional content is auth prerequisites and retention, which are constraints rather than usage guidance.

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