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

Annotations already declare read-only and non-destructive, but the description adds significant behavioral context: live data source, HTTP 503 with no charge when upstream data is unavailable, a $0.10 USDC per-call SLA, and a data_source field for provenance. This goes well beyond annotation coverage and provides agents with critical failure and cost information. 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 front-loaded with a clear purpose, but it repeats the HTTP 503 no-charge behavior twice: once with '>50% of fields' and once as 'when upstream data sources unavailable.' This redundancy is unnecessary and reduces conciseness.

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 simplicity (one optional parameter, no output schema), the description covers data sources, usage context, failure modes, cost, and provenance. It hints at output via 'Strong/moderate/weak consumer signal' but does not detail the response structure. Sibling tools follow a similar pattern, so the missing output schema details are less critical.

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 schema has a single optional parameter 'focus' with enum values, but the description's schema coverage is 0%. The description lists sentiment, spending, and saving categories that map to the enum values, giving indirect meaning. However, it does not explicitly explain how the 'focus' parameter affects the output, leaving the mapping implicit.

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 identifies the tool as providing live consumer sentiment benchmarks from FRED, enumerating specific indicators (University of Michigan sentiment, Conference Board confidence, retail sales, PCE, personal saving rate). This distinguishes it from sibling tools that focus on individual benchmarks (e.g., get_personal_savings_benchmark, get_retail_sales_benchmark).

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 provides clear context for when to use the tool: 'Strong/moderate/weak consumer signal for GDP and equity agents.' It implies that this aggregate benchmark is appropriate for broad economic analysis, while sibling tools cover individual metrics. However, it does not explicitly state when not to use it or name alternatives.

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