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

Annotations already cover safety (destructiveHint=false, openWorldHint=true), so the bar is lower; the description adds value by disclosing the return payload (checkoutUrl/portalUrl, plan metadata, quotas, instructions). It could go further on the payment lifecycle — e.g., that no charge occurs until the user completes checkout — and the stated 'idempotentHint: true' sits slightly awkwardly with 'generates a live 1-click session URL' each call.

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?

Front-loaded with the core action and output type, then dense supporting detail. The pricing/quota enumeration is long but each figure is decision-relevant for an agent choosing a plan; nothing is clearly padding.

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 carries the return-shape burden and does so (checkoutUrl/portalUrl plus instructions). Auth is covered indirectly by the schema's apiKey note. Minor gap: it doesn't state that the returned URL must be surfaced to the end user in a browser, which matters for correct handling.

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 description coverage is 100%, so the schema already documents all four parameters and both enums, making 3 the baseline. The description reinforces the plan tiers and adds one genuinely new fact — the $0.50 per extra connection overage — but otherwise largely restates the enum documentation rather than adding usage semantics.

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?

Names a specific verb (Generate) and concrete resources (Stripe Checkout session URL / Customer Billing Portal link), scoped to workspace subscription upgrades. The plan tiers and add-on are spelled out, so an agent can immediately distinguish this from account_register, account_status, and the other billing-adjacent siblings.

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?

The upgrade context is clear ('to upgrade a Nuntior workspace subscription') and the two modes are named, with plan choices enumerated. However, it never explicitly routes the agent — the checkout-vs-portal decision only appears in the schema's `action` description, and there are no stated prerequisites (e.g., must already have an account or active subscription) or exclusions.

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