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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description earns credit for adding the non-obvious resolution rule: it uses 'the latest business day on or before a date' rather than an exact-date match. It also discloses provenance and a source hash in the return payload, which is useful for auditability.

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?

Purpose is front-loaded in the first sentence, followed by return contents and usage examples. The second sentence is dense with a long enumeration, but nearly every clause carries distinct information; the closing disclaimer is brief and justified.

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?

There is no output schema, but the description enumerates the return payload (maturities, yields, canonical series names, spreads, curve-shape classification, provenance, hash), so an agent knows what to expect. With annotations covering safety and the schema covering inputs, nothing essential 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 coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema: the 'date' parameter is not an exact-match filter but a snap-back-to-latest-business-day anchor. That clarification materially changes how an agent picks a value for the parameter.

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 (build) and resource (nominal US Treasury constant-maturity yield curve) plus the exact source (Fed Board H.15 snapshot). It is clearly distinguishable from siblings like fed_board_h15_rate_history and fed_board_h15_rate_spread, which handle single series and spreads respectively.

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 invocation examples ('show today's Treasury curve', 'was the curve inverted on 2024-06-03?', 'compare short and long rates') and a scope exclusion ('Not security pricing or investment advice'). It does not, however, explicitly route the agent to sibling tools (e.g. rate_spread for a single spread series), so the when-not-this-tool guidance is incomplete.

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