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

Annotations already declare readOnlyHint/destructiveHint/openWorldHint, so the safety profile is covered. The description adds genuinely non-obvious behavior: oldest-first single-page pagination with since/next_cursor continuation, a $1M default notional floor, and the caveat that watcher uptime is unknown. It omits auth/permission or rate-limit behavior, keeping it below 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?

Front-loaded with 'Use for...' and packed with high-value facts in five compact sentences. The dense notional/pagination clarifications are each doing work, though the sentence order (uptime caveat last) is slightly less scannable than it could be.

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 8 parameters, 0 required, no output schema and 13% schema coverage, the description covers pagination, the notional floor and the data-reliability caveat, which are the highest-risk gaps. But it leaves the event enum values, coin format and address filter unexplained, so an agent still lacks a complete picture for calling all parameters 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?

Schema description coverage is only 13%, so the description must carry parameter meaning. It clarifies hours (1-168), min_position_notional_usd (default $1M, pass 0, and the important 'position size not incremental trade amount' distinction) and since's continuation semantics, but coin, event, limit, cursor and address are left entirely to the schema. Partial compensation warrants a 3.

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 states a specific resource and scope: observed position changes over 1-168 hours in the 'watcher cohort'. It also distinguishes itself from adjacent concepts by stating it is 'not alerts or an exhaustive live trade feed'. It does not name the specific sibling tools (e.g. get_hyperliquid_positioning) it differs from, so it stops short of a 5.

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 opens with an explicit 'Use for...' context and adds clear exclusions ('Not alerts or an exhaustive live trade feed'), which tells the agent when this tool is the wrong choice. However, it never names an alternative sibling to route to, so the when-to-use guidance is strong but not fully directional.

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