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

Annotations declare readOnlyHint=true, and the description adds valuable context: weekly refresh, trailing 90-day window, and the fact that it returns a score with two fields. It does not mention rate limits or error handling, but given the read-only nature, this is sufficient.

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 fairly compact but includes parenthetical details that all add value, such as severity category and data source. It front-loads the primary function and includes a clear 'call when' clause, though it could be slightly trimmed without losing meaning.

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?

The description explains return fields, data source, refresh cadence, and applicable use cases. No output schema exists, so the description appropriately covers the tool's behavior. It omits details on scoring methodology, but that is not essential for invocation.

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 coverage is 100% with the optional 'days' parameter fully described, including its purpose (returning historical series) and the Gold tier requirement. The main description adds no parameter details, so the baseline score of 3 applies.

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 returns a 0-100 FDA drug-recall velocity score based on trailing 90-day Class-I recall counts, with specific output fields (recall_velocity_score and class_I_90d). It identifies the data source (openFDA Drug Enforcement) and refresh cycle, making its purpose distinct from any sibling tool.

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?

Provides explicit when-to-call guidance: FDA drug recalls, Class-I enforcement acceleration, quality-system or supply-chain compliance risk, supplier audits, Form 483 responses, and pre-consent-decree or import-alert remediation. This is clear context for an AI agent to select this tool over alternatives.

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