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

Annotations already flag destructive/idempotent/write, and the description goes well beyond them: the last-owner invariant, the required x-api-key with team:admin scope held by an owner/admin, rejection of other token types, and the 403 on self-registration sandbox keys before claim. These are exactly the failure modes an agent must anticipate before calling a destructive tool.

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 is front-loaded in sentence one and each following sentence carries a distinct constraint. The middle sentence is long and comma-spliced, though every clause is load-bearing.

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 single-parameter destructive mutation with no output schema, the description covers auth, caller privilege, the last-owner guard, and workspace-claim state. It stops short of stating the observable effect (e.g., that the user disappears from list_team_members), which would close the remaining gap.

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% and the user_id description already points at 'user_id on a list_team_members result'; the prose adds no further detail on the parameter, so 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?

Opens with a specific verb+resource ('Remove a person from your workspace'), which cleanly separates it from invite_team_member, add_team_member and change_team_member_role in the sibling list.

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?

Gives explicit preconditions and exclusions: the last owner cannot be removed, and removal is refused for non-admin scopes, non-owner/admin callers, tokens, and unclaimed sandbox keys. It does not name the alternative tool (change_team_member_role) for cases where the intent is role modification rather than removal, so it stops short of full routing guidance.

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