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

Annotations only declare readOnly=false, destructive=false, openWorld=false; the description goes well beyond them by disclosing that nothing is broadcast, the permission requirement, the gasless typed-data payload variant, cross-chain via buyChainId, and Solana-specific quoting/signing behavior. That is exactly the mutation-safety context an agent needs before proposing a trade.

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?

Front-loaded with the core action and the no-broadcast guarantee, and every sentence carries operational content. It is dense rather than tidy — the Solana note lands last as an afterthought and mixes platform behavior with parameter guidance.

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?

For a 7-parameter mutation tool with no output schema, the description covers the reviewUrl hand-off, platform variants, and the escalation path to execute_swap. It stops short of saying what the tool returns besides reviewUrl (calldata vs typed data), which the agent must infer.

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 0%, so the description must carry parameter meaning, and it only partially does: it explains gasless (typed-data payloads), buyChainId (cross-chain), and the Solana wallet implication. chainId, sellToken, buyToken, sellAmount, and slippageBps receive no explanation at all, leaving half the surface inferred.

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 specific verb and resource ('Build a swap for the user to sign') plus the critical boundary 'Does not broadcast', which separates it from broadcast tools. It names the sibling it is not (execute_swap), so an agent can route without opening either schema.

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?

Explicit conditional routing: 'If hands-free trading is on, use execute_swap instead', plus the prerequisite 'Requires the "swap" permission' and the instruction to hand the user reviewUrl. The one gap is quote_swap, a close sibling whose distinction from this tool is never addressed.

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