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

Annotations already declare readOnly/idempotent/openWorld, so the safety profile is covered. The description adds genuinely non-obvious behavioral context: output is sorted high-to-low, includes exact unit, missing-value evidence, GeoFIPS, source hash, and attribution. It does not disclose rate limits or the 2–8 boundary's behavior at the edges, but it goes well beyond what annotations provide.

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?

Four sentences, front-loaded with the core action before examples and the scope caveat. Each sentence earns its place, though the enumeration of return fields is slightly list-like rather than tightly worded.

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?

There is no output schema, so the description carries the return-value burden and it does list key output fields (sorted values, unit, missing-value evidence, GeoFIPS, source hash, attribution). Combined with full schema coverage and read-only annotations, an agent has what it needs; only edge-case parameter behavior (e.g., duplicate/over-8 selectors) is left unaddressed.

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 schema already documents year, indicator (with example slugs), geographies, and response_format. The description restates the 2–8 state constraint and names example indicators, adding marginal value but no new syntax or format detail beyond the schema. Baseline 3 is appropriate.

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 states a specific verb (Compare) and resource (one official BEA SASUMMARY annual indicator across 2–8 requested states) for an exact year, and it bounds scope with 'It does not rank all states unless they are explicitly supplied.' This differentiates it from trend/profile siblings without needing to open any schema.

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?

Three concrete usage examples ('compare 2024 Texas and California GDP', 'which of these states had higher 2023 per-capita income?', 'compare regional price levels') make the intended call pattern obvious, and the closing sentence defines a scope limit. However, it never names an alternative sibling (e.g., bea_state_economic_trend) or states when to prefer one, so it falls short of explicit when/when-not routing.

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