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

Annotations flag a destructive, non-read-only, idempotent mutation; the description goes well beyond them by disclosing that adding takes effect immediately with no invitation or email, that removal triggers a type-the-site-name confirmation in the client's form, and that only owners/admins may call it. It also warns of the last-site side effect (removing them from the team) which is not captured by destructiveHint alone.

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?

The positive case and the return value are front-loaded, and every sentence carries information; the trailing parenthetical of exclusions is dense but each clause earns its place by preventing a specific misuse. Slightly long and nested, but not padded.

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 3-parameter mutation with no output schema, the description supplies the return value (the sites the member can see after the change), permission requirements, immediacy of changes, confirmation behavior on removal, and the edge cases that must be handled elsewhere. Nothing an agent needs to call it correctly 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 100%, so the schema already documents member identifiers, the sites array (id, name, or partial URL), and the view/edit/remove enum. The description reinforces the single-site removal constraint and the confirmation flow but adds no syntax or format detail beyond the schema, so baseline 3 applies.

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 (change which sites a member can see) and enumerates the three concrete outcomes: see more sites, view or edit a site, or stop seeing one. It also names the sibling tools that handle adjacent cases (invite_member, change_member_role), so an agent can distinguish it from them without opening a 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?

Explicit when-to-use (monitor-only member such as a client needing more site visibility) plus explicit when-not-to-use: someone not on the team → invite_member, an account-level member → change_member_role, a member's last site → dashboard. The owner/admin-only precondition is stated. This is close to a complete routing rule.

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