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

No annotations are present, so the description must cover behavior itself; it discloses per-call pricing ($0.02 USDC on Solana), the treatment of unpublished dates (null yield, never interpolated), and the hard snapshot cutoff of 2026-10-09, which is not covered. It omits the output ordering and whether the rows are ascending or descending, but the most important behavioral traits are disclosed.

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 leads with price and the core contract, which is good. The description also spends a full clause on the data source's licensing terms (free commercial redistribution), which does not help an agent invoke the tool, and the closing sentence about dates after 2026-10-09 repeats the range already given, so the description could be tighter.

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?

With four optional parameters, no annotations, and no output schema, the definition covers scope, null handling, and vintage, which is enough to call the tool safely. It never says whether results are sorted, whether limit trims from the end of the range, or what a row looks like, leaving real gaps for a series-returning 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?

The schema is fully described (100% coverage), which sets the baseline at 3. The description does add real value by stating that tenor selects exactly one series and that start/end are bounded by the 1990-01-02 to 2026-10-09 snapshot. It says nothing about limit, whose 'last N rows' semantics live only in the schema.

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 states a specific verb and resource: it returns one tenor's dated yield series for a requested start/end range. The scope and snapshot window are explicit. It never names or contrasts with the closely related siblings rates_curve, rates_spreads, or rates_schema, so an agent must guess which one to call.

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?

There is no guidance on when to use this tool rather than rates_curve, rates_spreads, or rates_schema, even though those tools fill the same subject area. The description gives no decision criteria, so the agent must infer from the name alone that this one returns a dated time series.

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