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

With destructiveHint=true and openWorldHint=true already set, the description still adds substantial disclosure: cadence changes/removals return checkoutUrl for cardholder approval and apply at next renewal, immediate additions charge prorated via secure checkout then activate only after settlement, already-paid service is not refunded, and credentials must never be collected in chat. It also states idempotency and canonicality expectations. This is well beyond what the annotations convey.

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 core purpose is front-loaded and each sentence carries operational weight (checkout flow, no refunds, credential policy, idempotency). It is on the longer side and includes generic boilerplate about canonicality and retry keys, but for a five-variant mutation tool the density is justified.

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?

There is no output schema, yet the description explains the key return (checkoutUrl), the approval/settlement lifecycle, prerequisites, idempotency and confirmation requirements. Nothing an agent needs to call this complex multi-action tool correctly is missing.

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 structured schema carries the parameter baseline (a 3). The description still adds semantic meaning the schema omits: what each action does to the recurring plan, that quantity for add_optional_service produces a prorated charge, and that confirm gates the destructive actions. Slightly short of 5 because it does not map every field (companyId, idempotencyKey, _corply_context) to its purpose.

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 precise verb+resource ('Manage the connected company's unified recurring plan') and enumerates the exact operations (change_cadence, remove_optional_service, add_optional_service, cancel_plan, open_payment_method). An agent can distinguish it from the read-only sibling get_company_billing and from manage_corply_mail_billing without opening the schema.

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 an explicit usage gate: invoke the mutating actions 'only after the founder explicitly requests that exact change,' plus a prerequisite (authenticated active company access) and a confirmation boundary. It stops short of naming alternative sibling tools (e.g., get_company_billing to inspect the plan first), so 4 rather than 5.

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