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

Annotations flag destructiveHint=true and readOnlyHint=false, and the description adds the material specifics: revoked seats don't touch the others, the new seat token is returned only once and cannot be re-fetched, seats share the owner's sites, and seat tokens are blocked from rotation, global revoke, seat management, recovery-email changes and billing. It also documents the plan_required error path for Free/Hobby callers and the upgrade link to surface to a human.

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 Pro-only gating and the one-time token return are front-loaded, and nearly every clause carries new operational information. It reads as one long run-on paragraph, though, so a small structural tightening (bulleted actions) would improve scanability without losing content.

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 still tells the agent what comes back (a list of seats; a one-time seat token on create) and what happens on failure (plan_required plus an upgrade link). For a 4-parameter, plan-gated management tool this covers everything needed to call it correctly.

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% and the schema already labels label/seat_id as create-only/revoke-only, so the baseline is 3. The description adds genuine meaning beyond the schema by tying token type to authorization scope ('the owner token revokes any seat, a seat token only itself') and noting the seat token is returned exactly once, which affects how the agent handles the response.

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 resource (named agent seats on a Pro account) with concrete scope (up to 5, each with its own token sharing the owner's sites) and the three operations it performs. An agent can distinguish this from the sibling revoke_token/rotate_token tools because the description explains seats are separately revocable and that seat tokens cannot rotate or revoke all tokens.

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?

It gives explicit per-action prerequisites: 'list' works with any token, 'create' needs the owner token plus a label, 'revoke' needs seat_id and the owner token to revoke any seat or a seat token for itself. What's missing is an explicit 'when not to use this' pointer to siblings (e.g. use revoke_token for a single token), so it stops short of a 5.

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