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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavior beyond that: national/uniform rows and USACE regional rows are automatically appended when a state is given, per-m2 conversions are flagged as computed:true, and residential remodeling quotes are explicitly out of scope. It omits any note on rate limits or result-volume behavior, but for a read-only aggregate query this is solid added context.

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 content is front-loaded with the core verb and resource, and each clause carries substantive information (layers, geo formats, augmentation rule, exclusion). The Japanese/English duplication roughly doubles the length, which is intentional for bilingual serving but does inflate token cost relative to a single-language version.

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?

With an output schema present and 100% parameter coverage, the description need not explain return values, and it correctly focuses on scope, layers, geo/period inputs, the auto-augmentation rule and the exclusion. Combined with the readOnly annotations, an agent has enough to call it correctly; only explicit sibling routing is missing.

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% with all 9 parameters documented, so the baseline is 3. The description's layer enumeration and geo/period examples (county:06037, cbsa:31080, Austin, TX, FY2026) largely restate what the schema already provides, adding volume of text rather than new semantics. No compensating meaning is introduced for the limit/offset paging behavior.

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 (query/pull) and resource (the U.S. public construction cost database) and enumerates the exact layers returned (labor, wage, work, equipment, index, spending, cost_sqft, cost_limit, bid_item, house_price, material), so an agent knows precisely what data it yields. It also carves out a scope exclusion ("not residential remodeling quotes"). It does not, however, differentiate itself from overlapping siblings such as get_jccdb_labor_rate, get_jccdb_work_unit_price, or get_us_prevailing_wage, which cover some of the same layers.

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 implies when to reach for it (broad multi-layer cost lookup by layer/geo/period/item) and notes one exclusion, but it gives no explicit when-to-use-vs-sibling routing despite many adjacent tools (get_us_prevailing_wage, get_jccdb_work_unit_price, get_us_permits, get_price_range). The pointer to get_jccdb_coverage appears only in the schema's layer field, not the main description, so the main text leaves routing to inference.

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