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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds non-obvious behavioral constraints that structured data cannot convey: the last remaining Owner cannot be demoted, and organization-inherited Owner roles cannot be changed here. These are exactly the guardrails an agent needs before attempting a mutation. It stops short of describing what the operation returns or how failures surface.

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?

Front-loads the core purpose in the first clause, then layers constraints in a compact sequence. Every clause carries information (permissions, edge cases) with no filler. It is dense but readable; the role-value ambiguity noted elsewhere is an omission rather than verbosity.

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 destructive mutation, the description covers permissions, the two most likely failure conditions, and the inheritance exception, on top of annotations that flag the operation as destructive and non-idempotent. With no output schema it need not explain returns. The remaining gap is the undocumented 'role' value set, which the description alludes to but never specifies.

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 67%, with the key parameter 'role' carrying no description and no enum. The description only incidentally hints at valid values ('Manager role', 'Owner role'), which partially compensates but does not enumerate what the agent must pass. The documented memberId/team_id parameters add no description-side value 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?

States a specific verb+resource ('Update an existing team member's role') that unambiguously identifies the operation. It is clearly distinguishable from the nearest sibling, removeTeamMember, and no other sibling performs member-role mutation. An agent can select this correctly without opening the schema.

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 supplies real prerequisites ('Requires the Manager role or above', Owner-only rules), which is useful usage context. However, it never states when to use this tool versus alternatives (e.g. removeTeamMember, inviteOrgMember), and gives no when-not guidance beyond the two edge cases. Usage is implied through permissions rather than routed explicitly.

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