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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so safety is covered. The description adds what annotations cannot: the exact filter semantics (excludes accepted and expired invitations), the authorization requirement, and the API-key scope.

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 short sentences: purpose and filter first, then permission, then return type and scope. No filler and nothing buried.

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?

Covers purpose, precise inclusion criteria, permission, auth scope, and the return type (array of InvitationDTO) in the absence of an output schema. Minor gap: it does not say whether results are ordered or bounded, though the tool exposes no pagination parameters to clarify.

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 100%, with account and workspace fully documented in the schema, so the description does not need to repeat them. It adds nothing beyond the schema—no note on how the account/workspace selection interacts with this workspace-scoped listing—so the baseline 3 applies.

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 (list), resource (invitations), and a precise scope: pending = not yet accepted and not expired, for the current workspace. That definition alone separates it from pm_send_invitation and pm_cancel_invitation, which act on the same object.

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 the caller prerequisite (MANAGE_USERS permission) and the API-key scope needed (users:read), which tells an agent up front whether it can call this. It stops short of naming alternatives (e.g., listing workspace members via pm_list_workspace_members, or canceling via pm_cancel_invitation), so routing is implied rather than explicit.

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