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

Annotations already declare this is a read-only, idempotent, non-destructive, closed-world operation, and the description adds meaningful behavioral context beyond that: short_bond is not cash, caveats note currencies missing a leg such as GBP borrowing the USD short-duration fund, source_currency reveals borrowed legs and currency risk, and disclaimer prevents the output from looking like personal advice.

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 purpose and then adds useful caveats and definitions. It is somewhat long for a zero-argument read, but the extra sentences about short_bond, caveat, source_currency, and disclaimer all carry substantive meaning rather than repetition.

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?

An output schema exists, so the description need not explain return values in exhaustive detail, but it still clarifies the important fields and caveats an agent should understand. Given the zero-parameter schema and rich annotations, the description is complete enough for correct selection and interpretation.

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?

This tool has zero parameters, so parameter semantics are minimal by design. The description does not need to document inputs, and the baseline for a no-parameter tool is appropriately met.

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 states that it returns the client's currency and the default instruments a build resolves in it, and it distinguishes this read from the sibling build_allocation_strategy by explaining that builds resolve these themselves while this tool reports what they would hold. The instrument categories and currency context are concrete enough for an agent to understand exactly what the tool exposes.

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 explicitly names the relevant alternative, build_allocation_strategy, and gives the precise condition for using this tool instead: 'this read is for when the client asks what they would hold.' That routes the agent correctly without requiring inference.

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