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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds two things beyond them: the search_events dependency for event_id and the fact that `get` returns rules and member count, which is useful pre-call context.

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?

The action dispatch is front-loaded as a tight bullet list with zero filler, which is the right shape for a polymorphic tool. The closing sentence repeats the event_id origin already stated in the schema, a minor redundancy.

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 and rich annotations, the description only needs to explain dispatch and prerequisites, and it does so for all three branches. Nothing required to call the tool correctly is missing.

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 the schema already documents event_id, group_id and page. The description largely restates that (event_id from search_events, group_id required for `get`) and adds little syntax or format detail the schema lacks; 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?

The description names a specific verb (read) and resource (user groups) and enumerates the three operations the single tool performs via `action`. It is clear enough to distinguish from mutating siblings like create_group/delete_group, though it never names an alternative tool explicitly.

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?

Each `action` value is mapped to a concrete intent (list all, fetch one with rules and member count, list rule fields), which is real usage guidance for a dispatcher tool. The prerequisite that event_id must come from search_events adds a concrete ordering guideline, but no explicit when-not-to-use or sibling routing is given.

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