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

Annotations only say readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true — they say nothing about atomicity or failure modes. The description adds the critical disclosure that the legs are NOT atomic, that there is no combined contract call, that each leg is a separately signed transaction, and that partial execution leaves the wallet with half the intended ratio. This is exactly the behavioral context metadata cannot carry.

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?

Four sentences, front-loaded with purpose and return shape before the operational rules. Every sentence carries unique information: what it builds, the swap_build equivalence, the non-atomicity caveat, and the sequencing rule with its rationale. No 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?

With no output schema, the description supplies the return contract ('{ legA, legB }, each a full SwapPlan exactly like swap_build's'), and for a nested-object, 4-required-param, open-world mutation tool it also supplies the two things an agent would otherwise get wrong: execution order and abort-on-failure. The remaining field-level detail is adequately covered by the 60% schema coverage.

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 60%, so the schema documents most parameters (amount vs amountRaw, receiver constraints, symbol resolution). The description adds only the conceptual mapping that each of legA/legB is 'a full SwapPlan exactly like swap_build's,' which clarifies the nested object shape but not individual field semantics. Baseline 3 is appropriate.

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 ('Builds signable/sendable plans for BOTH legs of a Double Out or Double In swap') and immediately disambiguates from the closest sibling by explaining it is 'two ordinary swap_build calls under the hood.' An agent can tell from the first sentence exactly what this produces and how it differs from swap_build.

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?

Gives explicit operational sequencing: 'Execute leg A fully first (steps, signing, report_execution) and confirm it landed before starting leg B,' plus a clear when-not rule ('If leg A fails or is rejected, do NOT execute leg B'). It implies the alternative (two separate swap_build calls) rather than naming it, and never mentions double_quote as the natural predecessor despite the quoteId param, so it stops short of full routing guidance.

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