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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is covered. The description usefully adds what the quote returns (merchant net after processor fee, plus the rate-fall headroom) and a guardrail against REST-style arguments. It does not discuss precision/rounding behavior beyond ceil_to_decimals or failure modes when direction and inputs disagree.

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?

The first sentence states purpose, then each mode gets one formula-dense sentence — front-loaded and efficient. A few closing sentences ('Follow its required fields and exact choices') are meta-boilerplate that repeat what the schema enforces, slightly diluting density.

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?

An output schema exists, so return values need not be re-explained, yet the description still sketches them, which helps. However, with a nested inputs object at 0% schema description coverage and a parameter with unclear conditional requirements, an agent still lacks guidance on defaults (buffer_pct, spread_pct, network_fee_paid_by) and on the decimals ceiling.

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 reported at 0%, so the description carries the burden, and it does give meaning to buffer_pct, network_fee, network_fee_paid_by, processor_fee_pct and spread_pct through the formulas. It leaves decimals, direction defaulting, and which fields are conditionally required per mode implicit rather than stated.

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 and action — merchant invoice conversion at a given rate — and spells out the exact formula for each direction (fiat_to_crypto vs crypto_to_fiat). It never names a sibling tool, so differentiation from the many other buscalc_* calculators rests on the phrasing alone, which keeps it just below a 5.

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 clearly maps each mode to its inputs: fiat_to_crypto uses invoice and optional network fee, crypto_to_fiat uses received with processor fee and spread. Invocation rules (fields inside inputs, supply units/modelVersion only when listed, follow required fields and exact choices, don't pass the REST calculator field) are explicit. It offers no when-not-to-use or named alternative, so it stops 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.