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

Annotations only declare it is a non-read-only, open-world, non-destructive write. The description adds substantial context beyond that: a real email is sent, the link is valid 7 days, invite_url is returned, plan gating applies, and re-inviting a pending address issues a fresh link.

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 core action and the side-effect warning, then permissions and edge cases. Dense but nearly every sentence carries distinct information; the dashboard analogy is slightly redundant with the title but aids recognition.

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 write tool with no output schema, the description covers side effects, return value (invite_url), permission model, plan requirement, and idempotent retry behavior. An agent has everything needed to call it correctly and safely.

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 description coverage is 100%, so role enum, defaults, email, workspace_id sourcing, and idempotency_key semantics are already documented in the schema. The description only reinforces that role should be confirmed with the user, adding little beyond the structured fields.

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 ("Invites someone by email to join a workspace as a team member") and anchors it to a known UI action ("like the dashboard's 'Invite member'"). It also explicitly distinguishes itself from the similarly named sibling list_workspace_people by clarifying these are login members, not tagged people.

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 preconditions and exclusions: confirm address and role with the user first, requires a Team plan, owners/admins can invite but only owners can invite admins or owners. It also names the alternative concept (list_workspace_people) and the re-invite case, leaving little to inference.

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