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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds real value beyond that with the permission model (self vs admin vs owner), which is the main behavioral question for this call. It omits consequences such as what happens to the removed member's resources or whether the removal can be undone.

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?

A single dense sentence with no filler. The core action is front-loaded and the permission rules follow immediately, so nothing needs to be re-read.

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 two-parameter destructive tool with annotation coverage and no output schema, the essential information — who can call it on whom, and the self-removal case — is present. Only edge-case effects (post-removal state, reversibility) are absent, which is a minor 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?

The org parameter is documented in the schema (with its default), leaving userId as the only gap; the description clarifies that userId equal to your own id means 'leave', which is genuinely useful semantics. With 50% schema coverage and only that one clarification, it sits at baseline rather than above it.

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 (remove) and resource (someone in the org) and captures the dual scope: removing another member versus leaving yourself via your own id. That scope distinguishes it from cloud_team_invite and cloud_team_role, though no sibling is named 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?

Gives explicit authorization conditions: anyone (including viewers) may leave, removing another member requires admin, and removing an owner requires an owner. It does not contrast with alternatives such as cloud_team_cancel for whole-team removal, so it stops short of full when-to-use guidance.

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