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

Annotations already mark this as readOnly, and the description adds meaningful behavioral context: the calculation method (rolling 12-month vs 12-month baseline), the neutral value of 50 representing 10% YoY, monthly updates since 1972, and the source_lineage field. It doesn't disclose rate limits or auth details, but the readOnlyHint covers the safety profile, and the added formula and cadence go well 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?

The description is efficiently structured in three sentences: definition/formula, usage scenarios, and update frequency. Each sentence contributes unique value, and the most important information is front-loaded. The parentheticals are dense but relevant, and there is no filler.

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 naming the return fields (score, source_lineage) and explaining the index's interpretation. It also covers update cadence and gives concrete example triggers ('score crossing 60'). It does not fully specify all possible score interpretation ranges, but it is sufficiently complete for an agent to select and invoke the tool.

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 schema description covers the only parameter (days) 100%, including its optional nature, purpose (daily history), and range. The tool description itself does not mention days, but because the schema fully explains it, the baseline of 3 applies. The description does not need to compensate; it adds no extra parameter meaning beyond 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?

The description opens with a specific verb ('Returns') and names a precise resource: the 0-100 Drug Labeling Volatility Index. It immediately defines the scope (rolling 12-month openFDA counts vs prior baseline) and outputs (score and source_lineage), which clearly distinguishes it from sibling tools without requiring comparative descriptions.

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 call scenarios: 'when the user asks about FDA drug label changes, labeling activity acceleration, safety label or prescribing-information updates, or pharma regulatory intelligence, or when timing review-queue expansion and label-change parsing workflows.' It does not state when not to use it or name alternative tools, so it stops short of a perfect 5.

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