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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true, but the description adds substantial context: the confirmationToken gate, the required organization:manage permission plus owner role, and the no-op behavior for existing members. It does not describe response content, though an output schema exists to cover that.

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?

Three dense sentences, front-loaded with the core action and side effect, then the precondition workflow, then permissions. Nothing is wasted, though the confirmation-token sentence is long and could be split for faster scanning.

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 tool with a required confirmation token, permission requirements, and an existing output schema, the description covers preconditions, side effects, idempotency-adjacent edge cases, and authorization. An agent has everything needed to call it correctly.

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 20% and the description compensates well for the key parameters: email semantics, the three role values, and the purpose of confirmationToken. organizationId and requestId are left to the schema (requestId is documented there), so it stops short of full coverage but adds real meaning.

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 and resource ('Invite someone to the organization by email with a role'), names the three allowed roles, and describes the resulting side effect (acceptance email). It is clearly distinguishable from siblings like list_members, update_member, and cancel_invitation.

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?

Explicitly prescribes the workflow: call preview_operation with tool "invite_member" and these arguments first, show the plan, and invoke only after explicit user agreement. It also states what happens on an already-member address (nothing, reported back), covering both when-to-use and an edge case.

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