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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true, and openWorldHint=true, so the description doesn't need to restate those. It adds meaningful behavioral context: email invitations can be created before the recipient has an account, and the recipient must explicitly accept after signing in. This goes beyond the schema and annotations, though it doesn't detail side effects like whether an existing collaborator is replaced or whether the invitation expires.

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 sentences, each carrying distinct information: the core action, the workspace-sharing special case, and the email-invitation behavior. No filler or repetition of schema fields. The most important scoping information is front-loaded.

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?

The tool has an output schema, so return values don't need explanation. The description covers the main behavioral nuances (email pre-account invitations, explicit acceptance, whole-workspace sharing). It could be more complete by noting what happens on duplicate invitations or whether the idempotencyKey prevents duplicates, but for an invitation tool with annotations and an output schema, this is largely sufficient.

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 only 33%, so the description must compensate. It does clarify the key parameter semantics: identity can be a username or email, entityType folder with rootFolderId enables whole-workspace sharing, and email invitations can target pre-account users. However, it doesn't explain workspaceId, idempotencyKey, or language beyond what the schema already says, so it doesn't fully cover the gap.

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?

The description states a specific verb ('Invite') and resource ('collaborator by NotePom username or email'), and distinguishes the tool from siblings like revoke_collaboration_invitation and accept_collaboration_invitation. It also clarifies the two entity types and the special case of sharing the entire workspace as a Drive, which makes the tool's purpose unmistakable.

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 explicitly tells when to use this tool (invite by username or email) and gives a concrete alternative path for sharing the whole workspace (entityType folder with rootFolderId from list_workspace). It also explains the email-invitation flow for recipients without an account, which is essential usage context not inferable from the schema.

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