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

Annotations already establish read-only, idempotent, closed-world behavior, so the description's real contribution is data provenance: verified against gov.uk, with source URLs, verification dates and a stated tax year (2026-27). That freshness and sourcing context is genuinely beyond the structured fields. It stops short of describing result shape or staleness handling.

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?

Front-loaded with what the tool returns and its verification status, followed by the trigger conditions. The one inefficiency is that the 17-category enumeration duplicates the schema's enum verbatim rather than just summarizing it.

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 one-parameter read-only lookup with no output schema, the description carries the needed burden: it says what the data is, what version it is, that it is gov.uk-verified with URLs and dates, and when to reach for it. Nothing required to call it 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% and the single category parameter already enumerates all valid values with an 'omit to list all' default. The description repeats the same category list without adding format or behavioral detail, so the baseline 3 applies.

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 and resource (current UK rates and thresholds) plus the payload returned: source URLs and verification dates. The category enumeration and the 'models reliably misremember these numbers' framing make it clearly distinct from computational siblings like take_home_pay.

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 an explicit and unusually thorough trigger list ('Use whenever a user asks about UK income tax, National Insurance...'). It does not, however, name when-not to use it or point to an alternative such as take_home_pay for net-pay calculations, so the routing guidance is one-sided.

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