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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuine value beyond that: it discloses the return content (which route applies, how far short of the threshold) and the legal basis for the computation, which shapes how an agent interprets the result.

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 purpose before the numeric rules, then the return shape, then the scope limitation. Each sentence earns its place, though the full statutory citation (Finance Act 2004 Schedule 11, SI 2005/2045 reg 28) is heavier than needed for selection.

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 must carry return-value burden, and it does — stating it returns the required figure per route, which route applies, and the shortfall. Numeric rules and the close-company treatment fill in the domain logic the agent needs to reason about inputs. Only minor gaps remain, e.g. no rounding/currency handling notes.

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 field meanings (partners, directors, shareholders, net_turnover, business_type, close_company) are already fully documented. The description contributes interpretive context (shareholders count alongside directors in a close company; thresholds applied per person) but no syntax or format detail beyond the schema, so the baseline 3 is warranted.

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 (checks) and resource (CIS turnover test for gross payment status), names the governing legislation, and precisely defines the computation (£30,000 sole trader; lower of £30,000 per partner/person and £100,000 otherwise). It is clearly distinguishable from siblings such as cis_deduction, cis_gross_up and cis_late_penalties, and it declares its output shape ('the figure needed by each route, which one applies, and how far short').

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?

Explicitly scopes the tool with a when-not clause: 'Covers the turnover test only, not the business test or the compliance test.' That tells the agent when this tool is insufficient (partial qualification assessment). It does not name sibling tools or state when-turnover-test-is-relevant preconditions, so it falls short of a 5.

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