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

Annotations already declare destructiveHint=true, openWorldHint=true and non-idempotent, so the safety profile is covered. The description adds genuinely non-structured context: 'Payment happens on a page the member opens' (the agent never handles payment), that pricingAcceptance must be the exact accepted value, and that the member, not the agent, performs cancellations. It does not disclose what a checkout mutates or the result of a completed purchase, keeping 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?

The content earns its place, but it is delivered as one long run-on sentence mixing actions, pricing sources, payment flow and cancellation policy before finally listing the action names. Front-loading the action vocabulary or splitting the policy text from the routing text would make it far easier to scan.

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 six-action destructive router with no output schema and only a generic params object, the description covers the essentials: the action vocabulary, where prices come from, that payment is member-side, and that cancellation is out of scope. The remaining gap — post-action return behavior and what each purchase changes — is a minor omission given the 'help' action exists for per-action fields.

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% and the action enum has no per-value description in the schema, so the description compensates by explaining what each action does and by pointing to action "help" for per-action fields. It also clarifies that params is free-form per action and that pricingAcceptance must be the exact accepted value. This is meaningful added meaning beyond the bare enum.

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 enumerates the six concrete actions (start_checkout, billing_portal, cancellation_feedback, buy_domain, buy_api_credits, buy_extra_campaigns) and states what each accomplishes, so an agent can tell it is a membership/billing action router rather than a read tool. It distinguishes itself from read siblings by naming get_account, get_membership and get_outreach as the pricing sources. It stops short of 5 because the opening sentence is a scattered list rather than a crisp statement of the tool's single job.

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 strong negative guidance: 'Cancelling is never done through an agent' and routes the member to the Membership page on applystead.com — a clear when-not. It also tells the agent where to obtain prices before invoking (get_membership preview, get_outreach packs). It doesn't explain when to choose billing_portal vs start_checkout vs cancellation_feedback, so it falls short of explicit alternative selection.

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