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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and non-destructive, so the safety profile is covered. The description adds meaningful context: verification via PumpPill's own price readings, multi-chain scope, and that data is 'a day behind members'. That latency disclosure is useful beyond annotations, but no rate limits or return-shape detail. Largely overlaps with what the schema/annotations establish.

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 criterion (2x/5x/10x/20x+) which is good, but the third sentence ('The best of the room, not its record...') and the closing 'A day behind the members' feel appended and slightly redundant with the opening. Sentences run long with stacked clauses.

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 read-only list tool with annotations covering safety, the description is adequate on scope and outcome definition. But 0% schema coverage, no output schema, and no parameter explanation leaves gaps an agent needs. The 'days' window default is undocumented anywhere accessible.

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 0% for both 'days' and 'chain' parameters, and the description doesn't explain either — no mention of the default 30-day window or which chains are valid (only implicitly 'Solana and Robinhood Chain' which does loosely map to the 'chain' param). With 0% schema coverage, the description should compensate but largely doesn't for the numeric window.

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 resource (the room's best calls) with a clear filtering criterion (reached 2x-20x+ after the post). Distinguishes itself from room_calls by explicitly positioning room_calls as the full list with losers. The framing is clear but the title/name 'best_calls' overlaps heavily and the phrasing is circuitous rather than direct.

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?

Explicitly routes the agent: 'the best of the room, not its record: room_calls is the full list with losers' tells when to pick this vs room_calls. However it doesn't cover the 'why' (e.g. use for showcasing wins vs full analysis) or conditions across other siblings like premium_calls_recent or outcomes_measured.

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