fda_drug_counts

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

Annotations already declare readOnlyHint=true, so the safety profile is clear. The description adds domain context (adverse events) and reinforces the aggregation behavior, but does not disclose additional behaviors like default limits, sorting, or pagination. It does not contradict the 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 efficient: a one-sentence core purpose, a one-sentence alternative pointer, and a focused bullet list of common fields. Every sentence adds value, and the list uses compact, consistent formatting.

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 aggregation tool, the description is well-rounded. It covers scope, key parameters with examples, and an explicit alternative. The absence of an output schema is mitigated by the clear 'count' semantics and the provided field examples. Minor gap: no mention of result ordering or default limit, but the schema carries the limit default.

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%, providing baseline 3. The description adds concrete example values for count_field (e.g., 'patient.reaction.reactionmeddrapt.exact') and search syntax, which are valuable beyond the schema's generic descriptions. This enriches parameter semantics enough to warrant a 4.

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 the tool's function: 'Aggregate/count FDA drug adverse event data by any field.' It uses a specific verb ('aggregate/count') and identifies the resource ('FDA drug adverse event data'). It also distinguishes itself from siblings by explicitly naming fda_count as the alternative for other endpoints.

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 description provides explicit 'when not to use' guidance by stating 'For counting other endpoints, use fda_count instead.' It also lists common count fields, which implies typical use cases. However, it does not explicitly contrast with fda_drug_events (raw event retrieval), leaving some ambiguity about when to choose counts over raw data.

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