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

Beyond the annotations, it discloses the 180-second `expiresAt` window, single-use semantics with the concrete consequence of address drift on rebuild, the fact that the server never holds keys or sends transactions, and the exact 422 `insufficient_balance` payload shape. The replay warning and the 'successful build is not a successful transaction' caveat are exactly the traits an agent would otherwise get wrong.

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?

Purpose is front-loaded in the first clause, then constraints follow in descending importance. It is dense but nearly every clause is load-bearing; the parenthetical error-shape detail is slightly heavy for a description but earns its place by enabling error handling without a failed call.

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 10-parameter, 6-required builder with no output schema, the description covers lifecycle (expiry, single-use), safety (no keys, unsigned), verification (simulate/`ok`), and the main failure mode. The remaining gaps are the amount units and the quote-vs-build relationship, which matter for a financial tool but are secondary to what is already documented.

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 already 80%, so the schema documents owner, slippage units, strategyId provenance, and the mode-scoped optional params. The description still adds value the schema lacks: slippage is conditionally required for `auto`, and the balance precondition is tied to which modes pull owner funds. It does not explain `repayAmount` / `withdrawAmount` units, which remain unstated in both places.

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 repay debt" states a specific verb (build) and resource (repay steps), and the mode sentence clarifies the two repay paths. It does not, however, distinguish itself from the sibling quote_repay or from build_close, so an agent must infer the quote-vs-build split on its own.

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?

Strong operational guidance: build immediately before signing rather than as a later plan, pass the result to `simulate` first, `auto` requires slippage while `manual` repays from the owner's wallet. What is missing is the upstream routing — nothing says to call quote_repay first or when to prefer build_repay over build_close for a position being wound down.

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