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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral caveat beyond that: 'Newest row update is not whole-cohort freshness' warns the agent the timestamp is not a cohort-wide freshness signal. It does not cover latency, cohort definition, or return shape.

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, no filler, with the primary use case front-loaded ahead of the caveats. The freshness warning is compact to the point of being slightly cryptic, which costs a point but keeps the entry token-efficient.

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 one-parameter read tool with annotations and no output schema, the description states what is returned (notionals and counts), the population (qualified cohort), the input format, and a freshness caveat. The main omission is that 'qualified cohort' is never defined, which could change how an agent interprets the numbers.

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?

With 0% schema description coverage, the description carries the full parameter burden, and it does so well: it says the asset must be an 'exact case-sensitive asset' and gives concrete examples ('BTC or xyz:NVDA') that illustrate the namespace-prefixed form allowed by the pattern. It does not explain the pattern's 'k' prefix variant or the max length constraint.

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 the exact resource and metrics returned (long/short notionals and counts in the qualified cohort for a given asset) rather than restating the tool name. It also scopes what it is not ('total exchange positioning or a price prediction'), which helps separate it from market-state siblings. It stops short of naming a specific alternative tool for those other needs.

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?

'Use for long/short notionals and counts...' gives a clear trigger for invoking the tool, and the negative scope statements rule out two misuses. However, it never names a sibling tool to use instead (e.g. get_futures_positioning or get_hyperliquid_market_state), so routing between near-identical positioning tools is left to inference.

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