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

Annotations already cover safety (readOnly, non-destructive, open-world, non-idempotent), so the description focuses on what annotations cannot express: newest-first ordering, the polling/paging idiom, and the crucial split between fields that are AS OF NOW (liquidity, smart-money flow) versus AT EVENT TIME (market cap, price). It does not cover rate limits or freshness lag for polling, which keeps it off a 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 the core definition and the change-vs-rank distinction, then field semantics, then the wallet-scope disclaimer. Dense and mostly waste-free, though the closing two sentences about `get_my_` tools are somewhat belabored for a point already implied by the prefix convention.

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 9-parameter, zero-required read tool with an output schema, the description covers everything an agent needs: what an event is, ordering, temporal field semantics, pagination strategy, and the scope boundary versus personal-data tools. Return shape is delegated to the output schema, as allowed.

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 89%, so the baseline is 3; the description still adds real semantic value by explaining how `after_timestamp` and `before_timestamp` are meant to be used (polling vs. back-paging) rather than just what they filter. It also clarifies the scope implied by `token_address` filtering ('omit for the whole market') implicitly through its whole-market framing.

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: a screener event stream of discrete token events (price/volume moves, notable activity) over a period, newest first. It explicitly contrasts itself with the leaderboards ('the event stream behind the leaderboards') and with `get_my_` tools, so an agent can place it against `get_screener_leaderboard` and `get_screener_event_filters` without opening a 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?

Gives an explicit selection rule — use it when the user asks what CHANGED or HAPPENED rather than what ranks highest now — which directly routes between this and the leaderboard siblings. It also names two concrete usage modes with their parameters: poll forward with `after_timestamp`, page back with `before_timestamp`.

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