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

Annotations (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint) already declare this is a safe, repeatable, read-only remote lookup, so the description needn't restate safety. The description adds that NAICS filtering is optional, but does not disclose return format, pagination, data vintage beyond the year param, or any CBP-specific caveats. With annotations carrying the safety profile, this is adequate.

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?

Three tight clauses: data source, optional filter, use cases. No filler, no repeated schema content, and the core resource is front-loaded. Every sentence earns its place.

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?

For a 9-parameter geographic data tool with 100% schema coverage and no output schema, the description covers what the data is but is thin on return shape and level/param interplay. An agent can probably call it correctly from the schema alone, but the description doesn't add much beyond the source name and use cases.

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 every parameter (msa, year, zcta, level, naics, place, state, tract, county) is fully documented in the schema. The description only reinforces that the NAICS filter is optional, adding no syntax, format, or level-dependency detail beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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?

Clear verb-less but specific resource statement: 'Business establishments, employment, and annual payroll from County Business Patterns.' An agent knows exactly what data is returned. It does not name a sibling tool (e.g., census_commute_employment or census_income_housing) to differentiate the dataset, but the CBP source naming is specific enough to distinguish it from generic census tools.

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 three use-case tags ('industry research, competitive intel, supply chain analysis') imply when this tool is applicable. However, there is no explicit guidance on when to choose this over census_commute_employment, census_demographics, or cost_of_doing_business_index, and no exclusions or prerequisites are stated.

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