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

Goes well beyond the readOnlyHint=true / idempotentHint=false annotations: it discloses the 180-second expiry with the `expiresAt` unix-ms field, single-use semantics (rebuilding an open predicts a different position address), that the server holds no keys and never sends transactions, and that a successful build does not guarantee a successful transaction. No contradiction with annotations, since building unsigned steps is genuinely a read of the chain state plus local assembly.

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?

Six dense sentences, front-loaded with the action and input contract, then constraints (expiry, single-use), then the safety caveat. No filler; each sentence carries an operational rule an agent must follow.

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, the description still tells the agent what comes back (unsigned steps, `expiresAt`) and what to do next (simulate). Only minor gaps remain, such as what an expired or already-used build returns as an error shape.

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 71% and the description closes the most important gap: `rewards` must be passed exactly as quote_claim returned them, and `compound` mode requires `slippage` (a conditional requirement absent from the schema). Remaining params (owner, chainId, positionAddress, strategyId) are left to the schema's own descriptions.

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?

"Build the steps that claim rewards" names a specific verb (build) and resource (claim steps), and immediately clarifies the return type: UNSIGNED transaction steps. An agent can distinguish it from quote_claim (which produces the rewards data) and from build_open/build_borrow (other build targets) without opening a 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 sequencing is given: take `rewards` from quote_claim, build immediately before signing, then pass `steps` to `simulate` and check `ok` before requesting a signature. It also states when-not behavior: don't build as a plan for later (180s expiry) and never replay a build.

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