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

Annotations already establish readOnly/openWorld/non-destructive, so the safety profile is covered; the description adds genuinely new behavior — that this is a polling endpoint with an expected cadence and a terminating condition (done is true), and that it exists precisely to track swaps execute_swap left unconfirmed. It stops short of saying what a failed/expired/refunded status looks like or how long it remains queryable.

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 short sentences with no filler, and the purpose leads. The only cost is readability: the first sentence is a long noun phrase rather than a clean statement, so the agent has to re-parse it before extracting the intent.

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 three-required-parameter read-only status lookup this is close to sufficient: purpose, cadence, terminating condition, and the not-needed case are all present. The gap is that it references a `done` field with no output schema to define it, and leaves chainId's expected value undocumented.

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 has to carry parameter meaning and only partly does. It clarifies that kind="solana" carries a Solana signature in `hash` and implicitly maps the enum to gasless vs cross-chain flows, but `chainId` is never explained — notably what value is expected for a Solana swap — and `hash` is otherwise undefined for the EVM kinds.

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 the specific resource (gasless/relayed, cross-chain/bridged, and Solana swaps) and states it reports where the trade 'stands', which an agent can read as a status check. It ties itself to execute_swap and the three kind values, distinguishing it from the quote/prepare siblings. The opening clause is grammatically tangled ('a Solana swap (kind "solana", its signature) that execute_swap left unconfirmed'), which slightly blunts the clarity.

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 gives explicit operational guidance: poll every few seconds until done is true, and it states the negative case — plain EVM same-chain swaps confirm on-chain and need no polling. No competing sibling tool is named as an alternative, but for this tool the alternative is simply 'don't call it', which is covered.

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