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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description does add real value beyond that: it discloses that costs for opening and closing both legs are netted in, that free-tier readings can be up to 15 minutes stale, and that rates change hourly so the result is a snapshot. It stops short of describing what the response contains (venues, fee breakdown, net rate) or any rate limits on call frequency.

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?

Three short sentences, front-loaded with the core promise and then the cost model and the freshness caveat. No repeated title text or filler; every sentence adds a distinct fact.

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 read-only, three-parameter screening tool with full schema coverage and no output schema, the description covers the two things an agent cannot infer: costs are netted and the result may be stale. The remaining gap is the unresolved overlap with delta_neutral_scanner and the absence of any hint about what the ranked result looks like, which prevents a fully confident selection.

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%, so pair, days, and size_usd_per_leg are already documented with defaults and bounds. The description adds only indirect meaning – 'net of opening and closing both legs at market' implies position size materially affects the answer – but says nothing about how holding days or size change the ranking. Baseline 3 is appropriate when the schema does the heavy lifting.

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 outcome: the best long/short pair across perp DEXs to collect the funding difference, computed net of opening and closing both legs at market. That is a clear verb+resource (find/rank a funding pair). It does not, however, distinguish itself from the near-identical sibling delta_neutral_scanner, so an agent still has to guess which of the two to call.

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?

There is no explicit when-to-use guidance and no named alternative among siblings such as delta_neutral_scanner, best_venue, or execution_plan. The only guidance is implicit – that this is a screening snapshot rather than a forecast – which tells the agent how to read the result, not when to select this tool.

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