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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so safety is covered. The description adds useful context: the required cenpy package, the optional free API key, and rate-limited fallback behavior when unauthenticated. That's real operational context beyond annotations, but the 'wholesaler_ids' and 'exclude_fillers' parameters hint at a completely different (fin/wholesaler) data model that the description never reconciles.

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?

Well-structured: metric list, then usage prompts, then requirements. Slightly verbose with the full Census variable code list, but every section is front-loaded and scannable. Minor bloat from repeating 'median_hh_income' style field names and prompt documentation.

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?

Has an output schema so return value explanation is not strictly needed, and the target audience (financial advisors scoring territory wealth) is clear. However, with a 0% schema coverage on a weirdly mixed parameter set, the description leaves an agent unable to know whether wholesaler_ids/exclude_fillers apply here or are inherited cruft.

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 0% across a parameter set that includes confusing fields (wholesaler_ids, exclude_fillers, source_resource_id) seemingly unrelated to Census data. The description names only state and zip_code implicitly and never explains how to use the fin-internal params or even whether they apply to this Census tool. With a 0% coverage gap, the description should compensate but does not.

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?

States a specific verb (Retrieve) and resource (US Census ACS income and wealth proxy data) with the exact entity scoped (ZIP code or state). No sibling tool touches Census ACS wealth data, so it's clearly differentiated. The enumerated key metrics reinforce the purpose.

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?

Provides an explicit 'Use this tool when' block with three concrete scenarios (scoring a territory, comparing income distribution, demographic proxy before AUM overlay). Strong context, though it names no alternative tool and gives no when-not-to-use guidance.

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