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

Annotations already declare read-only, non-destructive, open-world, and non-idempotent, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: historical reference periods, missing/suppressed data handling, explicit geography, payroll reported in thousands of USD, and ACS margins of error. It does not misstate anything the annotations claim.

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 purpose and dataset breakdown are front-loaded and earn their space. However, the trailing meta-instructions ('Put tool fields inside inputs', 'Follow its required fields and exact choices', 'Do not pass the REST calculator field inside MCP arguments') are invoicing/implementation boilerplate that reads as generic wrapper text and adds little semantic value for tool selection.

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?

An output schema exists, so return values need not be explained, and the description covers the remaining burden well: dataset capabilities, caveats about suppression and historical periods, and geographic scope. Given the high-complexity nested oneOf input, a short note on the `units` object and the dataset-dependent year enum would make it fully complete.

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?

With only 33% schema description coverage and a nested oneOf structure, the description must carry weight; it does partially by emphasizing explicit FIPS codes, noting industry is optional (default 00 all covered industries), and warning that units/modelVersion apply only when enumerated. It never explains the empty, locked `units` object or the year enum's dataset dependency, which are the schema's most confusing points. Baseline-to-slightly-above adequacy given the coverage gap.

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 and resource — retrieving Census County Business Patterns 2023 or ACS 5-year 2023/2024 estimates for one state or county via explicit FIPS codes — and enumerates what each dataset returns (establishments/employment/payroll vs. population/income/MOE). The data-source framing (Census CBP/ACS) makes it distinguishable at a glance from the BLS, USDA, and market-price 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?

Gives clear selection guidance between the two datasets by describing their contents, plus an explicit exclusion: 'not current market size or a complete competitor count.' It also constrains optional fields ('Supply units or modelVersion only when listed in inputSchema'). It stops short of naming a sibling tool to use instead for market-size or hourly-rate style questions.

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