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

Annotations already mark the tool read-only and non-destructive, and the description adds substantial behavioral context beyond that: counts are mentions not unique reports, VAERS reports are unverified, no causal inference is made, every response includes a disclaimer and is_causal:false. This is exactly the kind of interpretation risk an agent needs disclosed.

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 front-loaded with the core purpose and then adds necessary caveats. It is longer than average, but every sentence contributes: mention semantics, causal warning, disclaimer behavior, and the free-text exclusion. Slightly verbose but justified.

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 there is no output schema, the description adequately characterizes expected result behavior: counts by symptom, optional filters, top-symptom mode, and constant response attrs (disclaimer, is_causal). An agent has enough to select, parameterize, and interpret the tool's output without dangerous misreading.

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 100%, so the schema already documents all five parameters. The description adds useful emphasis on substring matching and on omitting symptom, but does not provide significant new per-parameter meaning beyond what the schema contains. Baseline 3 is appropriate.

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 and resource: counts VAERS report mentions by MedDRA symptom, with optional vaccine/year filters. The examples and the explicit 'Counts are MENTIONS' clarify exactly what is measured, setting it apart from the sibling vaers_event_s_by_vaccine and from free-text report retrieval.

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 clear usage guidance with concrete question examples and specifies when to omit symptom to see top symptoms. It also states an exclusion ('This never returns a single report's free text'), but it does not explicitly name an alternative tool for vaccine-centric or single-report queries, so it stops short of full when-not guidance.

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