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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description does add genuinely useful behavior beyond them — BigInt arithmetic with no floating point, meaning results are exact and deterministic — but it says nothing about error behavior for mismatched units or what happens when token_decimals is omitted for TOKEN units.

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 unit enumeration is front-loaded and the precision guarantee is stated immediately, which is the right priority order. The trailing three sentences are generic boilerplate ('Follow its required fields and exact choices') that dilute rather than inform.

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?

A nested-input conversion tool with an output schema and full read-only annotations needs only to explain domain scope and precision semantics, both of which are present. The remaining gap is minor: modelVersion is passed through without any indication of when or why an agent would set it.

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 has to carry weight, and it does clarify two things: all tool fields must be nested inside the 'inputs' object, and TOKEN/TOKEN-base requires accompanying decimals. However, it never explains modelVersion, token_decimals bounds (0-77), or the string-vs-number flexibility of price_per_coin beyond what the schema already states.

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 and resource ('Exact unit conversion') and enumerates the supported unit families (BTC/mBTC/bits/sat, ETH/gwei/wei, SOL/lamport, USDC, TOKEN), which makes the tool's domain unmistakable. It never names or contrasts a sibling like buscalc_unit_checks, so an agent must infer that the alternatives are for checking rather than converting.

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 context is only implied: the reader learns fiat valuation is optional and that TOKEN units need decimals, which hints at when the tool applies. The remaining sentences ('Supply units or modelVersion only when listed in inputSchema', 'Follow its required fields and exact choices') are invocation hygiene rather than when-to-use guidance, and there is no explicit exclusion or named alternative.

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