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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the description only needs to add operational detail. It does add two genuinely useful facts: aliases are not resolved, and bot traffic is filtered out unless include_bots is true, which materially affects result interpretation. It says nothing about pagination ordering, result caps, or the non-idempotent hint flagged in annotations.

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?

Three short sentences, front-loaded with the capability, then the two caveats, with zero padding. The one flaw is opening with the internal API name 'GetEventExplorer', which costs a few tokens without adding information an agent can act on.

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 explained, but for a nine-parameter tool with deeply nested filter objects and near-zero schema coverage, the description is too thin. It never explains how the two filter structures relate or how time_range interacts with paging, leaving the agent to guess at the most error-prone part of the call.

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 only 11% (just project_id), so the description must carry nine parameters and nested filter objects. It only clarifies include_bots and, indirectly, the alias behavior; the distinction between the top-level property_filters array and the nested events[].filters structure, plus time_range, distinct_id, session_id, and paging parameters, are left entirely undocumented.

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 concrete verb and resource ('returns a paginated, filterable list of events') and scopes it to 'across all users in a project', which implicitly contrasts with the per-profile siblings. It loses a point for not naming any sibling it is an alternative to, and for leading with the internal API name 'GetEventExplorer' rather than the tool's own name.

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?

There is no when-to-use / when-not-to-use guidance and no alternative tool is named, even though get_activity_feed, get_profile_sessions, and query_insights are plausible overlapping choices. Only two negative constraints are given ('does not resolve aliases', bot exclusion), which are behavioral facts rather than selection guidance.

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