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

Annotations already flag a mutating, open-world, non-idempotent, destructive operation; the description adds the two facts the annotations cannot convey — that an external email is sent and that the grant is pending owner approval rather than effective immediately. It does not cover repeat-invite behavior (relevant given idempotentHint=false) or failure modes, which keeps it at 4.

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?

Two sentences, both load-bearing, with the core action first and the approval caveat second. Zero filler.

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 two-parameter mutation with full annotation coverage and no output schema, this covers purpose, propagation scope, and the approval gate. What's missing is what a successful call returns or how the pending state is observed later, which an agent would need to confirm the outcome.

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 both parameters are already documented, including that board_id accepts an ID from list_boards or a board URL. The description only adds that the email identifies the invitee and that board_id's scope extends to nested boards — useful but marginal over the schema.

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?

Specific verb + resource ('Invite someone by email to edit a board'), plus a scope statement that the grant cascades to boards inside it. An agent can distinguish it from remove_editor or get_sharing without opening the schema, though it doesn't name those siblings.

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?

Usage is implied (grant edit access to a person by email) and the 'waits for the owner's approval' clause tells the agent the invite is not immediate. However, there is no explicit when-not guidance, no mention of who may issue invites, and no reference to the alternative of checking existing access via get_sharing first.

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