manage_workspace_member

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

Annotations only say destructive, non-read-only, open-world, non-idempotent; the description goes far beyond by disclosing that emails are sent, that access rights change, that API keys, AI app connections and webhooks stop when api_access is turned off, and that the owner is emailed on every change. Permission prerequisites (Manage team key, owner/admin caller), self-modification limits, and the owner-only rule for admin api_access are all stated, which annotations cannot convey.

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-loaded with the highest-stakes facts (sends email, changes access, preview first) before the per-action detail, and every clause carries operational information. The single dense paragraph makes the action branches harder to scan than a short list would, which is the only real cost.

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 an 11-parameter destructive mutation with no output schema, the definition covers the full call lifecycle: prerequisites, the preview/confirm handshake with preview_id, per-action parameter requirements, and side effects. Nothing an agent needs in order to call this safely is missing.

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 already 100%, so the baseline would be 3, but the description adds cross-parameter logic not present in the schema: which parameters pair with which action, that api_access works only with member_id on its own, and that omitting brand_ids on update keeps current brands. This is exactly the conditional composition an agent needs and the flat schema cannot express.

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?

Opens with a specific verb set and resource: 'Invite, update, or remove a workspace colleague,' then immediately distinguishes the three action modes. The namesake sibling list_workspace_members is referenced as the source of IDs, so the agent can separate listing from mutating without opening either 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?

Gives explicit branching guidance per action: invite requires email and role, update takes member_id or invite_id, remove accepts either. It also states hard exclusions the agent cannot infer: admin seats can only be granted in the posterly dashboard, and the mandatory preview-then-confirm workflow with a user approval gate.

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