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

No annotations are provided, so the description carries the full behavioral burden. It does add useful context — the data source ('openFDA data'), a disclaimer ('not medical advice'), and an explanation that Class I is the most serious — but it says nothing about result limits, pagination, or that this is a read-only lookup (inferable but unstated).

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?

A single dense paragraph that front-loads the resource and returned fields before moving to filters and provenance. Every clause carries information; only the trailing 'not medical advice' is marginally tangential, though still purposeful for a health data tool.

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 and no annotations, the description does the heavy lifting by enumerating returned fields (product, reason, status, dates, distribution) and naming the data source. The only meaningful gap is that the limit parameter's cap (1-50) and result-set behavior are left unexplained.

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 60% (days and limit have partial descriptions, firm has one, type and class have none). The description compensates by mapping filters to parameters — class, company (firm), and time window (days) — and by explaining the Class I/II/III severity ordering, which is genuine semantics the enum alone does not convey. It does not cover the limit parameter's meaning.

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?

States the specific resource (FDA drug and food recall enforcement reports) and enumerates the returned content: recall class, recalling firm, product, reason, status, dates and distribution. This is clearly distinguishable from sibling health tools such as health_drug_safety or health_drug_approvals, which cover adverse events and approvals rather than recalls.

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 says 'Filter by class, company and time window', which implies how to narrow results, but never states when to choose this tool over health_drug_safety or health_safety_signals, nor any exclusions. Usage is inferable from the resource description but not explicitly guided.

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