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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered by structured data. The description still adds real behavioral value beyond that: the output shape (Landed Drag Index with margin of error plus an evidence tier), the benchmark it measures against, and the access condition 'Free, no key' — the kind of auth detail annotations do not carry.

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 tight sentences: the first defines the measure and its benchmark, the second lists the inputs and the return shape, the third carries an access constraint. Nothing is repeated and the core purpose is front-loaded.

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 correctly compensates by naming what comes back (index, margin of error, evidence tier). It also covers the settled-versus-quoted distinction through the date input. What is missing is minimal — notably the currency-pair requirement and the optional custom mid override, both of which the schema carries.

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 all six parameters, including the optional midSpot override and the settledOn quote-vs-settled nuance, are already documented. The description restates three of them (amount sent, landed amount, date) without adding format or edge-case detail, so the baseline of 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?

The description gives a specific verb-plus-resource ('What a single cross-border payment costs, in basis points, against an independent mid-market reference') and names the headline output, the Landed Drag Index. It is clearly distinguishable from a generic cost calculator, but it does not explicitly differentiate itself from close siblings such as calculate_payment_cost or analyse_payment_leakage.

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?

Usage is implied rather than stated: 'give the amount sent, the amount that landed (or a provider says will land) and the date' tells the agent the required inputs and implicitly covers both settled payments and unaccepted quotes. There is no explicit when-to-use clause, no when-not, and no named alternative among the many sibling payment-cost tools.

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