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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description only needs to add behavior. It does: it discloses that pay rises and RPI are caller-adjustable assumptions, that output includes totals and sources, and that the result is a projection rather than a forecast — genuinely useful context beyond the annotations.

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?

Dense but front-loaded: the core deliverable is stated first, then the returned components, then the projection/advice caveat. Every clause carries information, though the trailing 'never says whether to pay a loan off early' slightly restates the 'information, not financial advice' clause.

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 7 parameters, no output schema, and closed-world annotations, the description does the needed work: it explains what is returned (projection, threshold, interest rate, total repaid, sources) and the nature of the result. It does not describe the projection's edge cases (e.g. balance never clearing, plan-specific write-off periods), leaving a small gap.

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%, so the baseline is 3. The description adds a conceptual layer the schema does not: which inputs are stated assumptions the caller may change (pay rises, RPI) versus fixed facts, and that the current threshold and interest rate are outputs. That framing meaningfully helps an agent reason about the parameters.

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?

The description names a specific resource (UK student loan repayments and write-off) and precisely what it produces: a month-by-month projection to the plan's write-off plus this year's threshold, interest rate, total repaid and sources. It is unambiguous, though it never explicitly contrasts itself with the near sibling calculate_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?

It gives clear context (assumptions the caller may change; a projection, not a forecast) and an explicit exclusion (it never advises on early repayment). It stops short of naming an alternative tool or stating prerequisites such as 'use this only after establishing the plan type', so it is context-rich but not fully routing.

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