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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so safety and idempotency are covered. The description adds valuable context beyond those: the data vintage ('2022'), the authoritative source ('U.S. Census', described as an 'edge dataset'), per-call cost ($0.008), the GET endpoint, and a preview of response content (title, hierarchy, children). It does not describe response shape or invalid-input behavior, but the annotation coverage lowers the burden.

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?

A single compact sentence packs purpose, source, vintage, cost, and endpoint with zero filler. The core function ('NAICS lookup:') is front-loaded, and every clause — Census source, 2022 edition, edge dataset, pricing, GET route — contributes new information not present in the schema or annotations.

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 simple two-optional-parameter tool with strong read-only/idempotent annotations, the description covers the essentials: what the code path returns, what the keyword path does, the source, and the price. There is no output schema, so the description's return-value preview is helpful; however, it leaves two minor gaps: behavior when neither 'q' nor 'code' is supplied, and the result shape for keyword searches.

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% — both 'q' and 'code' are already documented with type, examples, and descriptions, so the baseline is 3. The description adds only marginal meaning by framing 'code ... or keyword search' as alternatives and signaling that code is the hierarchical lookup path, but it introduces no format, constraint, or default details beyond the schema.

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 purpose: 'Official 2022 NAICS code → title, hierarchy, children; or keyword search' — a clear verb (lookup/search), a specific resource (2022 NAICS from U.S. Census), and the two operational modes. The NAICS domain is unique among the 30+ sibling tools, and the title 'NAICS lookup' combined with the output detail distinguishes it without ambiguity.

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 gives clear usage context by spelling out both invocation modes: you either supply a NAICS code to get title/hierarchy/children, or perform a keyword search via the alternative path. It does not state explicit when-not or alternative-tool guidance, but no sibling tool competes with NAICS classification queries, so no exclusion is needed.

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