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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the bar is lower. The description adds valuable behavioral context: data is 'cached', 'official', 'revision-aware', and includes provenance and age. It also clarifies that 'Daily fixings, annual context and licensed gaps remain distinct', which sets expectations about data granularity. No contradiction with annotations; the description enriches the safety and data-handling story.

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 three sentences, each packed with meaning. It front-loads the core purpose and then adds scope limitations. It is efficient but not overly terse; every sentence earns its place. Slightly dense but well-structured.

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?

The tool is complex with dual domains (FX and China series), and the description covers both. It mentions data provenance, age, and revision-awareness, which are important caveats. Since there is an output schema, return format is presumably defined. The description is sufficient for an agent to understand what data it will receive and what limitations exist (licensed gaps). Minor lack of parameter detail, but overall complete.

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 description coverage is 0%, so the description must compensate. It implicitly covers base/quote ('FX reference histories', 'currency crosses'), days ('daily fixings'), and china_series ('China annual economic series'), but it does not explain the 'provider' parameter (h10 vs ecb) or the exact meaning of 'days' range. The description provides overall context but leaves some parameter semantics to inference. Given zero schema coverage, this is a moderate gap.

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 the tool reads cached official FX reference histories and same-date currency crosses, plus China annual economic series. It specifies the exact resources and actions, and explicitly lists what it does not do (collection, model fitting, executable quotes, scoring), which differentiates it from potential siblings. The purpose is unambiguous and distinct.

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 gives clear context about what data is available and even provides exclusions (no collection, model fitting, etc.), but it does not explicitly name alternative tools or state when to choose this over a sibling like money_market_context. The 'Daily fixings, annual context and licensed gaps remain distinct' hint suggests scope but lacks direct routing guidance. So it's clear context without explicit alternatives.

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