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

Annotations already indicate destructive and readOnly=false. The description adds valuable behavioral detail beyond the annotations: removal does not revoke the agent's key, conversations, quota, or paid access, and membership cannot be restored without a new attach. Since it describes both what is affected and what remains, it goes beyond the structured flags and provides helpful side-effect 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 description is three short, purposeful sentences. The core action is front-loaded, the side-effect of preserved access is stated clearly, and the follow-up action (required reattachment) is given in one compact sentence. No filler or repetition exists.

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 simple two-parameter tool with no output schema, the description covers the main action, side effects, and the recovery route. It does not mention error conditions, how to obtain the team_key, or the exact queue behavior, but given the low complexity and the presence of the openWorldHint and schema descriptions, it is sufficiently complete for most correct invocations.

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 coverage is only 50% (team_key is described in the schema, but agent_id is not). The description says 'one member' but does not explicitly connect this to the agent_id parameter or explain how the team itself is identified (team_key). It does not add direct parameter meaning, so it only modestly compensates for the schema gap.

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 opens with a specific verb and resource ('Remove one member from a team') and further clarifies scope by saying 'you control' and 'its waiting queue'. It also distinguishes itself from siblings by explicitly mentioning that future coordination requires reattaching, which contrasts with the attach sibling.

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 gives a usage context: use this when removing a member from a team you control. It also points to the alternative action ('Future coordination requires attaching again'), though it does not explicitly state when not to use the tool or name the attach sibling directly. This meets the 'clear context, no exclusions' level.

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