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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds value by labeling the call FREE (a cost trait annotations cannot express) and by disclosing what the response contains, including Solscan tx links only 'when paid'. It stops short of describing pagination, result size, or what happens for a round with no entries.

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?

A single front-loaded sentence opens with the most decision-relevant token (FREE) and the resource, then lists contents compactly with no filler. The trailing enumeration is dense but every item corresponds to a distinct part of the payload.

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 one optional parameter, read-only annotations, and no output schema, the description carries the return-value burden and does so fully — scoring source, error metric, leaderboard flags, winner, and payout status are all named. An agent has enough to call this correctly and know what it will get back.

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 coverage is 100% and the single roundId parameter is already documented with its YYYY-MM-DD format and default to the current entry round. The description's 'scored or in-progress' phrasing reinforces that mid-round IDs are valid, but adds no format or edge-case detail beyond the schema, so the baseline 3 applies.

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+resource (return Arena round results) and enumerates what results include: closing prices used for scoring, per-prediction abs % error, leaderboard eligibility flags, prize-eligible winner, and payout status with tx links. It is clearly distinct from arena_submit_prediction, but it does not explicitly separate itself from close siblings like arena_current_round or arena_history.

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 or when-not-to-use guidance and no named alternative ('use arena_history for past rounds' is absent). The only implicit cues are 'scored or in-progress' and the schema note that roundId defaults to the current entry round, which hints at scope but leaves the agent to infer routing between arena_results, arena_current_round, and arena_history.

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