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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), so the description gets credit for adding real behavior: the enumerated verdict outcomes found / not_listed / not_out_yet / ask_branch, per-branch tax computation, and the empty-filter default. It stops short of explaining what each verdict means or how ambiguous matches resolve.

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 tight sentences with the core answer up front and the outcomes second, then the no-filter fallback. Dense but no filler; the enum-like verdict labels are used without definition, which costs a bit of 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 six parameters, no output schema, and no annotation detail on results, the description is the only source of return-shape information — and it lists verdict names without defining them (e.g., what makes a fee 'not_out_yet' versus 'ask_branch'). Adequate for calling the tool, thin for interpreting the answer.

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% with per-parameter descriptions, so the schema carries the load and baseline 3 applies. The description does contribute the flavor that 'level' and 'branch' jointly scope the price and that the month defaults to the current one, but that largely duplicates what the schema already states.

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?

Concrete: it says the tool resolves what a family pays for a branch/level/subject in a month, including per-branch tax, and returns one of four named verdicts. That is more specific than a restatement of the name. It never names how it differs from the sibling get_fee, so the read-one-vs-query-many boundary is left to inference.

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 only guidance is the default-scope note 'With no filters, every fee in force this month,' which implies a list/search shape. There is no statement of when to prefer this over get_fee, get_billing, or lookup, and no prerequisites or exclusions.

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