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

Discloses critical behaviors beyond annotations: billing owner restriction, immediate proration on the saved payment method, and the non-destructive nature of the first call. The description also explains that extra_seats is relative to current paid extra seats)Skip, which prevents off-by-one mistakes. Annotations indicate destructiveHint=trueholen, and the description aligns by showing confirm is required for changes.

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 dense sentences deliver purpose, authorization, billing side effect, and the exact confirm workflow with no wasted words. The critical 'relative' parameter semantics are front-loaded after the workflow, and every sentence earns its place.

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 destructive billing mutation with no output schema, the description covers prerequisites (billing owner), workflow (dry-run then confirm), side effects (proration on saved payment method), and parameter semantics. An agent can invoke this tool correctly without guessing, and the absence of an output schema is compensated by the explicit mention of the first-call response (price, proration explanation, Stripe link).

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?

Even though schema coverage is 100%, the description adds meaning beyond the schema: extra_seats is 'the ADDED number of seats relative to the current paid extra seats (use 1 to add one seat),' clarifying that the value is delta, not total. It also reinforces the confirm semantics from the schema, making the workflow unambiguous.

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: 'Add (or reduce) paid extra seats on the Team subscription' with clear purpose 'so more colleagues can be invited.' It also distinguishes itself from team_invite_member by focusing on billing seats rather than inviting members, and clarifies the direction of change with 'add (or reduce).'

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?

Provides explicit operational usage through the two-step confirm workflow: first call without confirm to obtain price and Stripe link, then call with confirm=true after user approval. It also states the authorization requirement ('Billing owner only'). It does not explicitly name sibling alternatives, but the billing-vs-invite distinction is enough to prevent confusion with team_invite_member.

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