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

Beyond the annotations, the description discloses that no funds move and nothing is created, that a fixed rate locks for about ten minutes, and that the tool says so rather than quietly substituting a float rate. It also tells the agent to relay warnings from the response. This is substantial behavioral context beyond readOnlyHint.

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 dense sentences, front-loaded with the core purpose and with no filler. Each sentence adds a distinct piece of information: core behavior, return value, fixed-rate special case, and side-effect-free guarantee.

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?

Given the output schema exists and the input schema already documents all parameters, the description is complete: it covers what the tool returns, how to choose direction, how to request a fixed rate, how the rate_id connects downstream to create_swap, and the fact that no funds move. An agent has everything needed to invoke it correctly.

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?

The input schema already covers 100% of parameters, so the baseline is 3. The description adds meaningful semantic framing: it explains the directionality of amount_from versus amount_to, the real-world meaning of rate_type 'fixed' and the rate_id it produces for create_swap, and reinforces that fixed availability is pair-dependent.

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 opens with a specific verb and resource: 'Ask what a swap would give, in either direction.' It clearly separates itself from sibling tools by mentioning that it returns a rate_id needed by create_swap and that 'Nothing is created and no funds move,' which distinguishes it from create_swap and swap_link.

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?

The description gives explicit usage direction: pass amount_from to learn the receive amount, or amount_to to learn the send amount. It also gives a clear selection rule for rate_type: use 'fixed' whenever the user wants a guaranteed number, and it explains the fallback behavior instead of silently returning a float rate. The connection to create_swap is explicit.

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