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

With no annotations present, the description carries the full burden and does so well: it discloses that transactions are unsigned, that the server never holds keys, the meaning of 409 states including the 'never pay the escrow again' hazard, Bitcoin-specific remainder/topUp semantics, feePayTo/feeAmountSats, and 503 as retryable. These are non-obvious operational traits that go well beyond the schema.

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 return type, then the operational caveats. It is dense and the parenthetical quota of 409 sub-states is heavy, but nearly every clause carries actionable information rather than filler.

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 two-parameter tool with no output schema, it explains the return material and the full signing/submission lifecycle, plus error-state handling. The one real omission is the semantics of id and the leg enum, which leaves the caller under-informed on inputs.

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 define both parameters, but it only gestures at 'leg' without explaining what a vs b mean and never clarifies that 'id' is the swap/RFQ identifier or what format it takes. An agent still has to guess at the two inputs it must supply.

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 the UNSIGNED transaction(s) to fund your leg') and immediately describes the return shape (EVM txs / BTC pay-to / TRON txs). It cleanly separates itself from broadcast_tx by explaining that it only produces signing material and that submission happens elsewhere.

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?

Explicitly chains the workflow: build here, sign with your own key, then submit via broadcast_tx. It also gives retry/stop guidance for 409 ('already funded', 'cannot fund yet', missing address) and 503. It does not, however, route between the other build_* siblings (build_claim, build_refund), which is the remaining ambiguity.

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