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

Beyond the annotations (readOnly/openWorld/non-idempotent), the description discloses the termination rule ('returns after max_events events or wait_seconds, whichever comes first'), the need to call repeatedly, and a non-obvious filtering exception ('launches are new coins, so they're never filtered out'). That is real behavioral context the annotations do not carry.

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 of core semantics followed by a purpose example and one payload note — front-loaded and nearly waste-free. The trailing 'With mints, each trade includes...' sentence is slightly detached from the main flow, costing a perfect score.

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 streaming tool with no output schema, the definition covers what comes back, when it stops, and how to continue, which is the essential contract. It stops short of describing the shape of each event record (except the trader/token detail under mints), leaving some uncertainty for an agent constructing a handler.

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 60%, and the description compensates by explaining the interaction between max_events and wait_seconds as a race condition, and by noting that supplying mints changes trade payloads to include the trader's wallet and token amount. It does not clarify min_sol boundaries or event-selection defaults, which remain schema-only.

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 verb and resource ('Wait on higher.fun's live feed and return what happens as it lands') and enumerates the event kinds (launches, graduations, buys, sells). The blocking/long-poll nature distinguishes it from snapshot-style siblings like get_trade_tape or get_coin_trades without needing to open any schema.

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 gives concrete when-to-use scenarios ('tell me when this coin graduates', 'watch for buys over 1 SOL', 'what launches next') and tells the agent to re-invoke to keep watching. It does not name an alternative sibling or state when *not* to use it, so it falls short of a 5.

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