recommend_exchange

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

Far exceeds the annotations (readOnlyHint/openWorldHint), which only cover the safety profile. It discloses the scoring model (weighted maker/taker fees, token and referral discounts, futures funding cost, fiat rails), the dynamic fiat weight growth 0.2→0.5, the zero-score penalty for venues lacking a direct rail, and the required inputs — exactly the behavioral context an agent needs to trust and interpret the result.

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 usage trigger, then the methodology and return shape, so the important content comes first. However, the bilingual duplication of the trigger sentence and the embedded version annotation ('v0.27') add length that is not strictly necessary.

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 compensates by describing the return payload (score, reasons, tradeoffs, advice, ranked alternatives). Combined with full schema coverage for 23 parameters, an agent has everything needed to invoke and interpret this tool.

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 100% across 23 well-documented parameters, so the schema already carries parameter meaning. The description only restates the required set (purpose, country, volume) and sketches the factors (volume, style, holding habits) without adding syntax or format detail beyond the schema — the baseline for high coverage.

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 precise verb+resource (recommend an exchange) and explicitly scopes the output: best option with score, concrete reasons, tradeoffs, actionable advice, plus ranked alternatives. This clearly separates it from sibling calculators like compare_total_cost and compare_exchange_fees, which produce comparisons rather than a personalized pick.

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 opening sentence gives an explicit trigger: use when the user is unsure which exchange to pick and wants a personalized recommendation based on their volume, style, and holding habits. It stops short of naming specific alternative siblings (e.g. use compare_total_cost for raw side-by-side numbers), so there is no explicit exclusion guidance.

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