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

Annotations already cover read-only/idempotent/non-destructive, and the description still adds substantial behavior the agent could not otherwise know: the quality filters baked into every result, the meaning of the two lanes, that the wallet list is window buyers rather than holders, and a self-critical backtest caveat ('most listed coins were below their listed price an hour later'). That caveat plus 'Not a recommendation' is exactly the kind of expectation-setting that annotations cannot supply.

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 'Free.' and the core definition, and nearly every clause carries information (filters, lanes, returned fields, caveat). It is weakened by a single 40+ word run-on sentence with stacked qualifiers and a mildly redundant 'For:' restatement of what was already said.

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 output schema, the description compensates by enumerating the returned fields (net SOL in, window buyers, largest buy, market cap, age, early concentration, and the list's own backtest). Combined with the filter disclosure and lane semantics, an agent knows what it will get and how to interpret it before calling.

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 100% and each parameter already carries a default, so the baseline would be 3; the description earns an extra point by defining what the lane values actually mean ('new (launched inside the window, curve not finished) and hot (any age)') and by confirming the default window of 6h. It does not clarify the 'both' lane value or how limit applies per lane, leaving a small gap.

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?

States a specific verb+resource+scope: 'pump.fun coins with the most SOL flowing in over the trailing window', then narrows with explicit inclusion filters (first-10s buyers <30%, <30% dust, real float, no launch-slot buyout) and two lanes (new/hot). It also distinguishes itself from the sibling check_coin by naming it as the follow-up rather than a substitute, so the agent can separate it from find_coin, launches_since and similar_launches without opening schemas.

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?

Gives concrete when-to-use triggers ('what is trending on pump.fun, what is hot right now, new coins with money coming in') and an explicit next step ('then check_coin on a mint'), which is real routing guidance. It stops short of contrasting itself with the closest list-generating siblings (launches_since, similar_launches, base_rate), so the agent must infer those boundaries.

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