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

With only readOnlyHint available, the description carries substantial extra load: it discloses units (percent, with a worked example), the 4h cache, the data source (Treasury.gov par yields with FRED fallback), and that OAS/UMCSENT were removed — all beyond what annotations or schema say. It stops short of stating freshness guarantees or failure behavior when the fallback triggers.

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?

Front-loaded with the critical "TWO DIFFERENT SHAPES" warning and every sentence carries information (shapes, default, units, removals, source, cache). It is on the dense side and leans on shouty capitalization, but no sentence is filler.

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, so the description must describe return values — and it does, for both modes, including the tenor range, the comparison dates, and the macro series mixed in. Combined with units and source, an agent has everything needed to call and interpret this tool.

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 a 3 is the baseline, but the description adds genuine meaning the schema omits: the parameter doesn't just "include history," it switches the entire response shape (parallel arrays over 11 tenors at three dates vs. a flat latest-value list mixing macro series). That materially changes how an agent should set it.

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 resource (US Treasury yield curve) and its scope (plus the wider macro dashboard), with unusually precise detail on what comes back. It does not, however, distinguish itself from siblings such as get_fred_data, which also surfaces FRED-sourced series — the description even mentions FRED fallback/series without clarifying the division of labor.

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?

It gives a real use case for the non-default mode ("for steepening/inversion work") and clearly marks the default, which implies when each shape applies. But it names no alternative tool and sets no explicit when-not-to-use boundary, leaving selection against get_fred_data or get_economic_calendar to inference.

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