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

With no annotations, the description carries the full transparency burden. It discloses that data is live, that the 5-min cache means slight delays, and that the tool provides 'inverted' flags as recession signals. It also explicitly instructs the agent to quote numbers verbatim and not rely on training data, which is a critical behavioral caveat. It doesn't mention rate limits or permissions, but for a read-only data tool the disclosed details are substantial.

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 description is concise yet information-dense. It starts with a high-level summary, lists all returned fields, provides a critical usage warning, mentions cache behavior, and points to an alternative—all in three sentences. No word is wasted, and the structure front-loads the purpose.

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 parameterless, schema-less, annotation-less tool, the description fully compensates: it lists all expected return fields, explains the recession-signal flags, warns about data freshness, and offers a sibling alternative. There is no ambiguity about what the tool returns or when to use it.

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?

The tool has zero parameters, so there is no parameter semantic to clarify. The schema is empty (100% coverage), and the baseline for 0-param tools is 4. The description adds clarity about output semantics instead, which is appropriate.

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 opens with 'Live US Treasury yield curve + recession-watch spreads + breakeven inflation,' which precisely names the resource and the data type. It enumerates the exact series returned (DGS1MO/3MO/2/5/10/30, 10Y-2Y, 10Y-3M, breakeven inflation, USD index), making it unmistakably distinct from other tools. It also differentiates from a sibling by directing users to tengu_v3_intel_risk_free_rate for a narrower view.

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 explicitly states when to use this tool versus an alternative: 'For a focused short-end + cash-park view, use tengu_v3_intel_risk_free_rate instead.' It also implies usage for broader curve and recession-watch analysis, and warns against using stale training data—clear guidance on when this live tool is appropriate.

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