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

Annotations already declare readOnly/destructive=false, but the description adds genuine behavioral context beyond them: idempotency (safe to repeat), canonicality (reads live server state, invents no facts), and an explicit confirmation boundary for this read. The card-number prohibition is useful operational context; only the templated 'confirmation boundary' enumeration edges toward boilerplate.

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?

Purpose and returned fields are well front-loaded in the first sentence, but the definition then carries three label-prefixed boilerplate blocks ('Prerequisite', 'Canonicality', 'Idempotency', 'Confirmation boundary') whose length is disproportionate to a simple read and partly restates the annotations.

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 read-only tool with no output schema, the description usefully enumerates what comes back (dates, services, pending changes, masked methods), which is the right way to compensate. The gap is the input side: with 0% schema coverage on a nested context object, the definition leaves parameter usage unexplained.

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 0% and the description never explains companyId or the _corply_context object (id/receipt). The phrase 'the connected company's' weakly implies the company is contextual rather than passed explicitly, but for two undocumented parameters including a nested object, that is insufficient compensation.

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 (Read) and resource (the connected company's unified billing account), then enumerates the concrete content: cadence, selected services, paid-through/next-renewal dates, pending changes, masked methods. An agent can distinguish this from manage_company_billing purely from the description.

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 a prerequisite (authenticated active company access) and a security rule (never solicit card/bank numbers in chat), which is real guidance. However, it never states when to prefer this over the sibling manage_company_billing, and 'plus every prerequisite stated above' is an opaque backward reference that gives the agent nothing actionable.

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