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

Annotations cover readOnly/openWorld/idempotent, and the description adds non-obvious behavioral truth: VAERS is unverified, counts are not evidence of causation, every response has `is_causal: false` and a CDC/FDA disclaimer, and free text is never returned. This is meaningful context beyond 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?

A bit longer than the minimal definition, but no sentence is wasted: output shape, parameter behavior, example questions, and critical caveats are all packed efficiently with the core statement front-loaded.

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 aggregate tool with no output schema, this covers what it returns, how to filter, how to discover valid codes, and the causal limitation. An agent has everything needed for correct invocation and interpretation.

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 already covers all 5 parameters at 100% with good descriptions. The description reinforces with concrete vaccine codes, the omit-vaccine behavior, and clarification that manufacturer is a substring match, adding practical value over the schema.

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?

Opens with a specific verb+resource: 'VAERS report counts and severity breakdown ... by vaccine'. It clearly stands apart from vaers_events_by_symptom and even defines its boundary with 'This never returns a single report's free text.'

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 explicit when-to-pass-vaccine vs omit-to-browse instructions, optional manufacturer substring matching, and example questions it answers. It doesn't name the sibling symptom tool directly, but the intended use is unambiguous.

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