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

Annotations already cover read-only, idempotent, non-destructive behavior, and the description adds real value on top: it is free, capped to a rolling one-hour window, ordered oldest first, and it reveals a 'next_since' cursor for polling that appears nowhere in the input schema or annotations. It stops short of describing rate limits or the response envelope.

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?

It is front-loaded ('Free. The last hour's pump.fun events'), then detail, then use-cases, then the polling rule, with no filler sentences. The long parenthetical enumerations each carry distinct information about what an event record contains.

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 carries the return-value burden and does so by describing the payload of each event kind. The one gap is the response envelope itself — it references a 'next_since' cursor without stating what else comes back or how the cursor field is named or placed.

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%, so the baseline is 3, but the description adds workflow meaning the schema lacks: 'Poll with since = next_since' explains how the cursor is meant to be used across successive calls, and 'as they land, oldest first' clarifies the ordering that 'since' interacts with.

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 ('the last hour's pump.fun events as they land, oldest first') and enumerates all four event kinds and the fields each carries, so an agent can tell it apart from siblings like launches_since, graduations, or today_live without opening 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?

The 'For:' clause gives concrete triggering questions (did the dev sell, which devs are dumping, what just launched or migrated) and the polling instruction tells the agent how to keep consuming the stream. It does not explicitly say when to prefer a sibling (e.g. launches_since for a wider window, graduations for older history), which keeps it below a 5.

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