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

Annotations (readOnlyHint=false, openWorldHint=true) establish the mutating/open-world profile, and the description adds real value on top: it clarifies that request_plan 'files a request for super-admin approval — never grants,' which prevents the agent from assuming access is provisioned. It also discloses that topup/checkout calls return hosted Stripe Checkout URLs, i.e. an external redirect consistent with openWorldHint. It stops short of stating auth/permission requirements or idempotency, so a 4 rather than 5.

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, front-loaded with the resource and return contents before the parameter-driven modes; capitalized verbs (RESOLVE, COMPLETE, TOP UP, REQUEST) aid scanning. There is mild redundancy between the parameter descriptions in the schema and the description text, but nothing is wasted enough to impair readability.

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-value burden and does so by listing the status fields returned and noting that certain parameters yield a hosted Checkout URL. The behavior of all three optional parameters is covered, and nothing an agent needs to invoke it correctly is missing. It could be more complete on the shape of the returned plan/price data, but for a zero-required-parameter tool this is solid.

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 each parameter's meaning, and the description does not repeat this gratuitously. It does add value beyond the schema by enumerating the valid plan keys (starter|pay_per_use|pro|max|enterprise), which the schema lacks as an enum, and ties each parameter to its resulting action. Baseline 3 is exceeded by that added semantic detail.

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 names a specific resource (company billing/plans) and enumerates the exact data returned: wallet balance, pay-per-use flag, license tier, per-action prices, purchasable and approved-but-unpaid plans. It also makes clear this is a multi-mode tool (read status, top up, request plan, complete payment), so an agent knows exactly what it is. No sibling in the list is billing-related, so no differentiation is needed.

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 states the operative scenario explicitly ('Use this to view or RESOLVE a 402 without leaving the connector') and then routes between the three modes by parameter: checkout_request_id to complete an approved plan, topup_amount to top up, request_plan to file a plan request. The when-to-use condition for each mode is unambiguous.

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