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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It clearly states the output will be rankings of gainers and losers, and ranks are ordered (implied by 'ranked'), which helps set expectations. However, it does not disclose any caching behavior, time window, or whether results are live or delayed. Most critically, the description invents a quoting structure ("Use for ...") that reads like a usage hint but provides no behavioral facts, such as pagination or output format. An agent cannot reliably predict what fields each row contains without an output schema reference.

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?

The description is compact—a single sentence plus quoted example phrases. It front-loads the core value proposition. The quotes take up space without adding much semantic value beyond natural-language examples, but they are not padding. A 4 feels right: it's efficient, though the quoted block adds a little noise.

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 tool has an output schema (so return fields are defined there) and only one parameter, the description is close to adequate. But with schema coverage at 0%, the single parameter 'limit' is entirely undefined, and the description adds no detail. The tool is a market-wide mover list; an agent could call it correctly for top movers, but might misuse 'limit' or misunderstand the return shape. A score of 3 reflects that it passes for a simple call but leaves a minor gap on the parameter.

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 schema has a single integer parameter 'limit' with a default of 10, and schema_description_coverage is 0%. The description does not explain what 'limit' controls (number of items returned, presumably) or any bounds. Since the schema provides no descriptions for the parameter, the description should have compensated—it does not. An agent must guess at the semantics of 'limit'.

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 clearly identifies the tool's purpose: listing top-gaining and top-losing crypto perpetuals, ranked across the whole market. It distinguishes the market-wide scope from sibling tools like market_snapshot or perp_dashboard, which likely have narrower or different scopes. It stops short of a 5 because it doesn't explicitly contrast against any sibling, leaving some differentiation to inference.

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 includes example natural-language invocations ('top crypto movers', 'biggest crypto gainers and losers today'), which implicitly tells an agent when to call it. However, it provides no explicit guidance on when NOT to use it or which sibling tool to prefer instead. The context is implied but not made explicit.

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