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

Goes well beyond the annotations by spelling out the calculation chain (trading allowance comparison, income tax bands, PA taper, Class 4/Class 2), the return contents (line-by-line working, payments-on-account warning, missed expenses, rates with GOV.UK sources, result card) and a caveat that it is an estimate, not tax advice. The annotations already cover safety, and the description reinforces it with "Read-only: stores and sends nothing" plus non-obvious behavior like Budget 2026 rules for 2027-28.

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 tax-year scope are front-loaded before the input list and the return description, and no sentence is pure filler. The single dense block of parentheticals is justified by a 19-parameter tax calculation, though it could be broken into shorter clauses for scanning.

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 complex, high-parameter tax estimator with no output schema, the description covers inputs to collect, the computation performed, the shape of the returned working and the legal disclaimer. An agent can decide whether to call it and how to populate it without opening anything else.

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 explains every one of the 19 parameters, including defaults, enums and the mileage rates. The description mirrors those expense categories (materials, tools, mileage, parking, phone, PPE, training, insurance, accountant) rather than adding new semantics, and only the trading allowance thresholds add genuine extra information for parameter interpretation. Baseline 3 is appropriate.

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?

Opens with a specific verb+resource ("Estimate a UK CIS subcontractor's tax refund") and bounds the scope tightly with tax years, inputs and the sole-trader/not-limited-company restriction. It does not, however, contrast itself with the sibling get_cis_tax_rates, leaving the boundary between "estimating a refund" and "getting rates" to be inferred.

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?

Gives clear usage context (self-employed sole traders under CIS, explicitly not limited companies) and names the required inputs as a checklist, which is effectively a prerequisite list. It stops short of saying when to reach for get_cis_tax_rates instead, so the alternative-routing guidance is absent.

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