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

Annotations already declare a read-only, idempotent, closed-world pure calculation, and the description is consistent with them. It adds real behavioral context beyond the annotations: the tax year, the excluded income components, the jurisdiction gap, and the fact that a taxpayer income rank is included in 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 compact sentences, no filler: capability first, then scope limits, then exclusions and the extra return value. Every clause carries information an agent needs.

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 does note that a historical income rank is returned, but it does not describe the main figures returned (net pay, tax and NI breakdown) or currency assumptions beyond GBP in the schema. For a read-only calculator this is close to complete, with a minor gap on the return payload.

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 67%, and the one undocumented parameter, mode, has no description in the schema at all. The description compensates by spelling out the two semantic directions (tax from a salary vs. salary needed for a target net), which is exactly the ambiguity mode resolves.

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 computation (employee income tax and National Insurance for 2026/27) and names both directions it supports: gross-to-net and net-to-gross. Sibling tools (adjust_for_inflation, compare_public_spending) are unrelated calculations, so no differentiation is needed.

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?

Explicit geographic applicability ('England, Wales and Northern Ireland only; Scotland is unsupported') and explicit exclusions (pensions, student loans, benefits) tell the agent when this tool is valid and what it will not model. It does not name alternatives or when-not-to-use cases, but none of the siblings compete with it.

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