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

Annotations are thin (readOnlyHint/openWorldHint only), so the description carries the load and does so well: non-custodial ('we never hold funds'), unsigned and caller-signed ('you sign and send it'), priority fee included, and an explicit $0.005 USDC x402 charge per call. It stops short of failure modes, transaction expiry, or default slippage behavior, which keeps it from a 5.

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, front-loaded with what is produced and followed immediately by the trust model and the price. No filler and nothing redundant.

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 and 20% parameter coverage, the description usefully compensates by naming the return shape (base64 versioned transaction, expected and minimum output) and the custody/pricing model. The remaining hole is input semantics — token identifier format and amount units — which an agent needs to call it correctly.

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 only 20% (wallet is the sole documented field). The description mentions 'for your wallet' and alludes to slippage via 'minimum output' but never explains whether from_token/to_token are mint addresses or symbols, what unit the string amount uses (decimal vs lamports), or the default slippage when slippage_percent is omitted.

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 concrete verb+resource (builds a ready-to-sign Solana swap transaction) and specifies the artifacts returned: a base64 versioned transaction with priority fee plus expected and minimum output. It implicitly separates itself from the quote-only sibling by promising a signable transaction, but it never names solana_swap_quote/swap_build, so sibling differentiation is inferred rather than stated.

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 only implied: the mention of 'best Jupiter route' and 'expected and minimum output' hints this is the execution step after a quote, and the cost line gives a budget signal, but there is no explicit when-to-use versus solana_swap_quote, no prerequisite ordering, and no when-not-to-use guidance.

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