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

Annotations carry the read-only/idempotent/non-destructive profile; the description supplements this with the latest-business-day rollback rule, the self-hosted snapshot source, and the exact computed outputs (spreads, shape classification, provenance, source hash). No annotation contradiction.

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 sentences: purpose, return contents, usage examples/caveat. No filler and key discriminators are front-loaded.

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 2-param tool with no output schema, the description spells out all return categories and gives representative queries. Only minor absence is explicit behavior when date is omitted, but optionality is already encoded by schema (required=0).

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?

Input schema already documents date format and response_format enum at 100% coverage; the description adds the important semantic that the date resolves to the latest business day on or before it. That is meaningful beyond the schema, justifying 4 rather than baseline 3.

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?

Opens with a specific verb ('Build') and names the exact artifact (nominal US Treasury constant-maturity yield curve) plus source (FRB H.15 snapshot). It enumerates returned components, which differentiates it from sibling H.15 tools (rate_history, rate_spread, search_series).

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?

Provides three concrete query examples ('show today's Treasury curve', 'was the curve inverted on 2024-06-03?', 'compare short and long rates') and the non-advice disclaimer. However, it never explicitly tells the agent when to prefer a sibling such as fed_board_h15_rate_history or rate_spread, so it stops short of full routing guidance.

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