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

Annotations already declare read-only and idempotent behavior; the description adds useful non-obvious context by warning that refresh is manual and the data is not a live feed. It also discloses that the output includes aggregate coverage statistics plus a sample of top vaccines, which goes beyond the bare annotations.

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?

The description is a single focused passage that front-loads the core contents, then adds the recency caveat and sibling pointer without repetition or waste. Every clause earns its place.

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?

Given that the tool has no parameters, no output schema, and is a simple read-only metadata endpoint, the description covers everything an agent needs: the exact statistics returned, the freshness caveat, and the intended next-step sibling. Nothing important is missing.

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 has zero parameters and 100% schema coverage, so parameter semantics are a non-issue. The description appropriately explains what the output contains rather than needing to clarify 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 clearly states this is a coverage/metadata tool for the VAERS pack: it returns total unique reports, year range, distinct vaccine types/manufacturers, seed load time, and top 5 vaccines. It differentiates itself from event-level siblings by explicitly pointing to vaers_events_by_vaccine as the next step.

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?

It gives a concrete usage context: check this tool before relying on recency because the data is manually re-downloaded, not a live feed. It also suggests the top-5 output as a starting point for vaers_events_by_vaccine, but does not explicitly say when to avoid it or address alternatives like vaers_events_by_symptom.

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