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

Annotations already declare read-only, idempotent, non-destructive behavior, so the description's job is to add context — and it does: a fixed 20-item cap, a 30-day lookback window, and 'aggregate counts only' signaling that no per-agent data is exposed. It stops short of saying whether results are ranked by count or what the payload looks like, but the value-add is real.

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?

A single sentence with zero filler; the 'Free:' qualifier and the result cardinality are front-loaded so an agent scanning it immediately knows cost model and output size.

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 no-parameter, no-output-schema aggregate read, the description supplies the essentials: what is counted, over what window, how many items, and that only aggregates are returned. Only the ordering/sort semantics of 'top' remain slightly underspecified.

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?

The tool takes zero parameters, so the baseline is 4. No parameter semantics are needed, and the description correctly spends no words on inputs.

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 concrete resource (top 20 coins requested for monitoring) with explicit scope (last 30 days, aggregate counts only), which is far more specific than the title. It implicitly contrasts with the sibling request_asset (which submits a single request) but never names that relationship, so an agent must infer it.

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 leading 'Free:' token hints at a paid tier among siblings like get_pricing/get_teaser, and 'top requested' implies a discovery/popularity use case, but no sentence says when to call this versus request_asset or the brief tools. Usage is implied rather than instructed.

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