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

Annotations cover safety (readOnlyHint=false, destructiveHint=true, openWorldHint=true), but the description adds genuinely non-obvious behavior: recipient emails are sent either way, existing users get immediate access while others get an invite, and there is a preview mode without confirm. The Pro-feature/pricing caveat is also disclosed. It stops short of describing the returned result shape.

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?

Four sentences, front-loaded with the core action and branching behavior, and each sentence carries useful information (roles, account handling, confirm gate, Pro constraint). Slightly dense but no 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?

With no output schema, the description correctly covers the observable effects (emails sent, immediate vs invited access, preview-without-confirm) plus ownership and plan requirements. It leaves role-permission nuance and error/return behavior to inference, but is close to complete for a 4-param mutation tool.

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 50%: role and confirm are documented in the schema, boardId and email are not. The description reinforces role options and confirm semantics (moderately overlapping the schema) and implies the board-ownership requirement for boardId, but adds little format or constraint detail beyond what the schema already provides.

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 ('Shares a board the user owns with someone by email') and constrains scope to email-based grants with EDITOR/VIEWER roles. It implicitly distinguishes itself from siblings like set_public_link (email vs public) but never names or contrasts those alternatives explicitly.

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 clear usage conditions: the caller must own the board, the recipients may or may not have accounts (handled differently), and it must be a Pro account on the web. It doesn't say when to prefer revoke_access or other sharing siblings, but the operational preconditions are well stated.

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