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

Annotations already signal read-only, idempotent, and non-destructive behavior, so the description adds value by disclosing that partial leg failures are noted rather than fatal, describing the classification output, and flagging that it is informational synthesis rather than legal advice. No contradiction with 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 longer than minimal but every sentence contributes functional information: sources, output shape, failure handling, scope exclusion, and disclaimer. It is front-loaded with the one-call purpose, though the closing 'Premium cross-source synthesis' phrase is mildly promotional and could be trimmed.

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 well by specifying the returned classification levels, recall severity logic, litigation metrics, complaint volume, and itemized interpretation. It also covers failure behavior, out-of-scope cases, and an explicit alternative, making it nearly self-sufficient 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 description coverage is 100%, and the schema already documents manufacturer, since, state, and company alias. The description reinforces that the tool keys on manufacturer/brand and mentions FDA severity and litigation time windows, but it adds little parameter-level 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?

Description names a specific resource and action: product-safety + liability read for a manufacturer/brand. It enumerates the three data sources (CPSC/openFDA recalls, CourtListener litigation, CFPB complaints) and the rolled-up output, which clearly differentiates it from single-source siblings like cpsc_recall_search or cfpb_complaint_aggregations.

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 positions the tool as a one-call cross-source synthesis and explicitly routes vehicle recall needs to recall_screen. It does not exhaustively enumerate when to prefer this over each single-source sibling, but the scope and alternative guidance are clear enough for an agent to choose correctly.

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