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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior, so the bar is lowered. The description still adds substantial behavioral context: it joins three public-record legs, notes that a failed leg is 'noted, not fatal,' explains the rolled-up risk output, and clarifies the weighting of FDA Class I/death-related recalls. This far exceeds annotation coverage.

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 but every clause adds operational value: the lead sentence defines scope, then it itemizes data sources, output structure, failure handling, sibling distinctions, scope exclusions, and a disclaimer. Nothing is redundant; the structure is front-loaded with the core purpose and then layers detail.

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?

Despite lacking an output schema, the description explains the return shape in concrete terms: LOW/MODERATE/ELEVATED risk read, complaint volume, top products/issues, recall count with FDA Class I/death severity, and litigation hits total + last-3-years. It also covers failure behavior and clarifies this is informational and not legal advice. An agent has enough to call it and interpret results.

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%, so the input schema already documents company, since, and state fully. The description does not add much parameter-specific meaning beyond naming the company/brand focus and mentioning that 'since' applies to FDA recalls. Baseline 3 is appropriate because the schema carries the parameter documentation burden.

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 opens with a specific verb+resource: 'One-call CONSUMER-RISK read for a company or brand, LED by the consumer-complaint picture.' It clearly differentiates itself from product_liability_screen and recall_screen, and specifies the exact data legs involved. An agent can immediately understand what this tool does and how it differs from nearby siblings.

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 names alternatives and provides exclusion criteria: 'This is consumer-complaint-centered and distinct from product_liability_screen' and 'NHTSA vehicle recalls need a specific year+make+model so are out of scope here (use recall_screen for a vehicle).' This gives the agent actionable routing guidance without needing to inspect other tool definitions.

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