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

Annotations already declare readOnlyHint=true and destructiveHint=false, meaning the tool is safe. The description adds valuable behavioral context: it returns HTTP 503 when upstream data is unavailable (with no charge), includes a data_source field for provenance, and states the per-call cost. This goes beyond the annotations without contradicting them.

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 front-loaded with the core content but contains redundancy: 'Returns HTTP 503 (no charge) if upstream source unavailable for >50% of fields' is repeated as 'Returns HTTP 503 (no charge) when upstream data sources unavailable.' Pricing info is useful but could be more concise. The structure is acceptable but not tight.

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?

Despite lacking an output schema, the description lists the key return items (yields, bp changes, spreads, inversion signal, SOFR, curve shape) and important context (source, failure mode, provenance, cost). The main gap is inadequate explanation of the 'tenor' parameter, which is relevant to using the tool. Overall, the description is fairly complete for a read-only data 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 has one parameter 'tenor' with enum values (2y, 10y, 30y, all) and no description (0% schema coverage). The description does not explain what 'tenor' controls or how it affects the output. Additionally, the description mentions '1M through 30Y yields' but the enum lacks 1M or other short-term tenors, which could confuse users unless 'all' is understood to cover them. The parameter semantics are left entirely to 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 clearly identifies the tool as providing Live US Treasury yield curve data with specific details (yields, spreads, inversion signal, SOFR, curve shape) and the source (FRED). This specific verb and resource description distinguishes it from siblings like get_agricultural_commodity_benchmark or get_fx_rate_benchmark.

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 provides clear context: it's for US Treasury yield curve data, live from FRED, with specific contents. While it doesn't explicitly name alternatives, the specificity makes the intended use case evident. It also notes when the tool will fail (503) and cost, which aids usage decisions, though it lacks explicit exclusions.

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