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

With readOnly/idempotent/openWorld annotations already covering the safety profile, the description adds real value: it discloses external provenance (central bank / treasury published curves), the unit convention (decimals, not percentages), the averaging window behavior, and a cost signal ("Free"). It does not mention refresh cadence, data staleness, or failure behavior if a source is unavailable.

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?

Content is front-loaded with the return shape and then the source options; the trailing "Free." is a deliberate, useful one-word signal. The main sentence is long and stacks parenthetical clauses (Svensson curve, IDW base rate, par yields), which slightly hurts scannability.

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 3-parameter read-only tool with no output schema, the description covers what is returned (per-maturity latest and average), the unit convention, and the source choice. Remaining gaps — exact response shape, behavior on missing maturities or unavailable sources — are modest for a lookup tool that carries clean annotations.

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 only 33% (only `maturities` is documented in-schema), so the description must compensate, and it largely does: it enumerates the three sources by institution (mapping to the enum) and explains that rates are averaged "over recent days (90 by default)", pinning down average_over_days. The maturity default list is left entirely to the schema, and the parameter names themselves are never echoed, so mapping requires a small inference step.

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?

Names the specific resource (risk-free curve: latest rate per maturity plus a trailing average), the three concrete sources (Bundesbank Svensson, ECB AAA, US Treasury par yields), and its role as the input to valuation_wacc. An agent can tell what it returns and where it fits without opening the sibling tool.

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?

"For the cost of capital ... ready for valuation_wacc" gives clear usage context and names the downstream consumer, so an agent knows this is the rate-fetch step before a WACC/DCF. However, it never states when a different source or a different valuation tool (e.g. valuation_benchmark, valuation_fx) would be preferred, nor any exclusion.

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