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

Annotations already cover the safety profile (read-only, closed-world, non-destructive), so the bar is lower. The description adds genuinely non-obvious behavior beyond that: the YoY value is service-computed (computed:true) and absent from the source data, and the no-filter case returns a list rather than empty results.

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?

Core behavior, computed-flag caveat, and fallback mode are front-loaded, with the example last. The full bilingual duplication roughly doubles length, which is justified for a JP/US dataset but adds no new information per line.

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-shape explanation is unnecessary, and the description supplies the two behaviors an agent must know (computed YoY, list fallback). Minor gaps remain around pagination/interaction of limit with list mode, but nothing critical for correct invocation.

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 baseline is 3; the description goes further by explaining the conditional role of query and source_id (absent both, the tool lists series) and showing accepted period formats via the example. It does not clarify how country/limit interact with the list mode.

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 (returns a series over a period) and resource (construction cost index series: NHCCI, PPI, construction deflator), and includes the distinctive YoY-change feature. It also distinguishes itself from get_jccdb_coverage by pointing there for source ids and from the broader observation tools by falling back to a series list.

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 explicit branching: with query/source_id use them, without either it lists the series, plus a concrete example call. It points to get_jccdb_coverage with detail:true as the alternative for source ids, but does not contrast with close siblings like get_jccdb_observations or get_jccdb_dataset_info.

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