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

Beyond the readOnlyHint annotation, the description discloses several crucial behaviors: match_confidence distinguishes exact NDC matches from name matches, the 'never silently returning' guarantee protects against misidentification, HTTP 503 (no charge) when upstream sources are down, and data_sources[] provenance with synthesis.output_hash. It also provides pricing (SLA cost) and an illustrative example, offering rich operational transparency.

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 information-dense yet compact. Every sentence adds value: use case, return fields, behavioral guarantee, example, source, SLA/cost, error behavior, and provenance. It is well-structured, starting with the primary use and flowing to operational details, with no fluff or redundancy.

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?

Given the minimal schema (one parameter, no descriptions) and no output schema, the description offers a comprehensive picture: what inputs are accepted, what outputs to expect, how errors surface (503), and how provenance is disclosed. It also explains the match_confidence semantics and gives a realistic example, making it fully self-contained for an agent to use effectively.

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 input schema has only a single string parameter with zero description coverage (0%), so the description must fully compensate. It does so by stating the parameter accepts either an NDC or drug name and provides a concrete example ('NDC 41163-703-10'), clarifying the expected format. This gives the agent exactly what it needs to invoke the tool correctly despite the bare 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 clearly states the tool's function: retrieving FDA drug recall status for an NDC or drug name. It specifies the target users (pharmacy, supply chain, compliance agents), the key return fields (status, classification, reason, dates), and the unique guarantee of not silently returning a different product's recalls. This goes beyond a generic statement and distinguishes it from siblings like get_fda_recall_history.

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 explicitly starts with 'Use when a pharmacy, supply chain, or compliance agent needs FDA drug recall status,' providing clear context for when to invoke the tool. It does not, however, explicitly mention when not to use it or name alternative tools, so it falls short of the highest bar for exclusionary guidance.

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