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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral context the annotations cannot: data is delayed up to 15 minutes, results are a 'Top' subset rather than exhaustive, and the field set is itemized. It does not say how many rows are returned or whether the delay differs per field, which keeps it from a 5.

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?

Two sentences, front-loaded with the FREE tag and the resource identity, then the field inventory, then the paid alternative with its price. No filler, no repetition of the title, and the delay caveat is folded into the field list rather than taking its own sentence.

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 parameters and no output schema, the description carries the burden of describing what comes back, and it does so by enumerating fields, disclosing the 15-minute delay, and pointing to the paid sibling. What is missing is the size of the 'Top' set and the sort order, which an agent would need to interpret results 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 tool takes zero parameters, so the schema has nothing to explain and the baseline is 4. The description correctly adds no parameter detail, and the field list describes output rather than input, which is appropriate since there is no output schema.

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 names a specific resource (tradeXYZ / Hyperliquid HIP-3 equity perps) and enumerates the fields returned: mark, 24h change, funding APR, OI, volume. It also contrasts itself with the sibling stock_perps, which is the paid full-coverage variant. The only ambiguity is 'Top' — the count and ranking criterion are not stated.

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?

It makes the free-versus-paid tradeoff explicit: this tool gives a teaser of top perps, while stock_perps at $0.003 returns every HIP-3 stock perp with large trades. That is a clear routing rule. It stops short of stating exclusions such as rate limits or whether the free tier caps results per call.

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