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

Annotations declare destructiveHint:false, which aligns with the semantics of removing a member from a group without destroying data—no contradiction. The description goes beyond annotations by disclosing the required permission and bulk execution behavior. It stops short of covering edge cases like idempotency or behavior when the member doesn't exist.

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, focused sentences that are fully front-loaded with the primary action first, followed by permission and bulk notes. Minor redundancy: 'Delete Member From User Group' and 'Removes a member from the specified group' convey the same idea; combining them could save a clause, but nothing is wasteful.

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?

For a relatively simple 4-parameter mutation with no output schema (so return-value documentation is unnecessary), the description covers the essentials: what it does, permission prerequisite, and batch capability. The main gap is clarifying the group_id vs group_ids usage, and edge/error behavior, but this doesn't detract significantly for a tool of this complexity.

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?

With 0% schema description coverage (all four parameters, including `account` and the `group_id`/`group_ids` overload, are structurally undocumented), the description had to compensate. The bulk note adds some meaning to `group_ids`, and the phrase 'from the specified group' implies `group_id` identifies the group. But the description doesn't clarify the relationship between `group_id` and `group_ids` (mutually exclusive? precedence?), nor provide formats for `email` or `account`.

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 uses a specific verb+resource pair ('Delete Member From User Group' / 'Removes a member from the specified group'), making the operation clear. It also naturally differentiates from siblings like elevenlabs_add_member (the inverse) and elevenlabs_remove_rules by identifying the exact entity being removed.

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 clearly states the required `group_members_manage` permission, which is actionable prerequisite guidance. It also hints at usage context via bulk support note ('accepts group_ids for batched execution'). However, it doesn't explicitly contrast with alternatives or list cases when not to use it.

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