Audit Admin Accounts

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

Annotations already declare readOnlyHint=true, so the safety profile is covered; the description adds real behavioral context beyond that: recursion into nested groups by default, the `nested=False` opt-out, and that only groups that actually exist are returned with `member_count`. It does not mention cost/latency of recursive expansion or permission requirements, which keeps it below a 5.

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 tight sentences: purpose first, then what is returned, then the single parameter behavior that changes results. No filler and nothing buried.

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 needn't be documented, and the description covers the key behavioral dimension (recursion) plus the group-existence filter. The remaining hole is the undocumented `domain` parameter, which an agent must guess at.

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 0%, so the description must carry the load. It does explain `nested` well ('list only direct members instead of recursing'), but `domain` is never mentioned in either the description or the schema — its null default and what null means are left entirely to inference.

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 ('Audit administrative accounts: members of well-known privileged groups') and immediately clarifies how it differs from the sibling `get_privileged_groups` by adding per-group attributes, `member_count` and expanded `members`. An agent can distinguish it from `get_privileged_groups`, `group_members` and `is_member` without opening a schema.

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 phrase 'Builds on `get_privileged_groups`' implies the relationship, and the `nested=False` sentence gives one concrete usage switch. However, it never states explicitly when to choose this over `get_privileged_groups` or `group_members`, nor any prerequisites (e.g. domain must be reachable). Usage is inferable but not spelled out.

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