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

Annotations only declare readOnlyHint=false; the description adds real behavioral context beyond that — the effect is immediate ('Their key stops reaching your company at once') and it is restricted to owners. It leaves out whether the action is reversible, how to re-add a removed person, and what the call returns.

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?

Two short sentences with the primary action first, the secondary case second, and the effect and permission constraint folded in without filler. The capability tag is compact metadata rather than noise.

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 mutation with no output schema, the description covers what it does, who may call it, and the immediate consequence. Only the reversibility/aftermath and the result of the call are unaddressed, which are minor gaps at 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?

Schema coverage is 50%: the company parameter is fully documented in the schema, while email carries only format constraints. The description implies email identifies the person being removed or whose invite is cancelled, which adds a little meaning, but it adds no syntax, matching, or lookup guidance beyond the schema.

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 concrete verb+resource pair ('Take someone off your team') and adds the second case ('cancel an invite you sent'), which clearly separates it from invite_member and list_team. It stops just short of naming those siblings explicitly, so it is clear but not maximally differentiated.

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?

It states the two situations that call for the tool (removing an existing member, cancelling a pending invite) and supplies the key prerequisite '(owner only)'. It does not name alternative tools or warn about cases where removal is the wrong action, so guidance is strong but not exhaustive.

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