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

Even with annotations already declaring readOnlyHint and non-destructive behavior, the description adds substantial operational detail: it returns a CLEAN/WATCH/ELEVATED LIABILITY SIGNALS rollup with specific metrics, treats a failed leg as non-fatal, ranks FDA Class I/death-related recalls as high severity, and clarifies it is informational public-record synthesis, not legal advice. This goes well beyond what annotations convey.

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 and front-loaded with the core purpose, then systematically covers inputs, outputs, failure behavior, exclusions, and caveats. It is longer than necessary for a simple tool, but the complexity of a three-source composite screen justifies most of the length. Minor redundancy exists in the closing 'Cross-source synthesis; informational public-record synthesis' phrasing, but overall each sentence earns its place.

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 tool's multi-source complexity and the absence of an output schema, the description is remarkably complete: it names every input leg, the returned rollup levels, the specific metrics included, how severity is assessed, how partial failures are handled, and the key out-of-scope case with an alternative tool. An agent has enough context to invoke this tool correctly and interpret its response at a high level without additional documentation.

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%, so the schema already documents all four parameters, but the description adds meaningful context beyond that: it explains that the manufacturer is the keying dimension across all three legs and provides concrete examples (Peloton, Fisher-Price). It also clarifies that 'since' bounds the FDA recall leg and 'state' scopes the CFPB complaint leg, which aligns with and reinforces the schema descriptions.

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 as a one-call product-safety and liability read for a manufacturer or brand, and it enumerates the three data legs joined: CPSC/openFDA recalls, CourtListener litigation, and CFPB complaints. It also distinguishes itself from vehicle-specific recall tools by explicitly excluding NHTSA vehicles and naming recall_screen as the alternative. The verb 'read' plus the resource scope makes the purpose unambiguous.

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 explicit when-to-use context: for a manufacturer or brand needing a cross-source public-record synthesis. It also provides a clear when-not-to-use rule: NHTSA vehicle recalls require a specific year+make+model and should go to recall_screen instead. This directly helps an agent route between this composite tool and its more specialized siblings.

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