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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, covering the safety profile. The description adds meaningful behavioral context beyond that: it details the specific fields returned, clarifies that all products with the same active substance are jointly assessed, and mentions the fixed regulatory schedule. It does not discuss pagination or data completeness nuances, but the annotation coverage lowers the burden.

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 dense but every sentence contributes: definition, return fields, positioning relative to other EU signals, and concrete example queries. It is front-loaded with the core purpose and avoids filler or repetition of parameter names already in the schema.

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?

With no output schema, the description compensates by listing the returned fields and giving real example queries. It covers the main intents and provides enough context about the PSUSA procedure. Missing a small note about default behavior when no query is supplied, but the schema examples and parameter docs largely fill that gap.

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?

Input schema description coverage is 100%, so all four parameters already have semantic definitions in structured form. The description reinforces that `query` is about active substance or medicine names, but it does not materially add to the schema's parameter documentation. Baseline 3 is appropriate here.

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 opens with the full expansion of PSUSA and a concrete explanation of what the procedure is, then states explicitly that it returns active substance, medicine names, procedure number, regulatory outcome, and dates. It goes beyond a generic label by framing the tool as 'the closest structured EU signal to a pharmacovigilance safety review', which differentiates it from siblings like ema_referrals or ema_chmp_opinions.

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 gives clear trigger intents through example questions: 'when was the last PSUSA outcome for X', 'has ibuprofen had a periodic safety update review', and 'recent EU pharmacovigilance outcomes'. It does not explicitly name alternatives or state when not to use the tool, but the context is strong enough for an agent to recognize the intended use case.

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