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

With no annotations, the description must carry the full load. It usefully discloses that the data is free, end-of-day (not live), sourced from Frankfurter/ECB reference rates, and limited to ~30 currencies — real behavioral context. It says nothing about authentication, rate limits, behavior for unsupported currency codes, or which date's rate is returned.

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?

Two short sentences, front-loaded with the standout fact ('FREE'), then scope, then examples, then provenance. No filler; the only slight waste is the trailing source attribution, which is nonetheless routing-relevant.

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 2-param read tool with no output schema, the description covers what the tool is, its scope, its data vintage, and its source. The remaining gap is the return shape — whether it returns a scalar rate, a rate plus effective date, or a currency pair object — which matters since no output schema exists to answer that.

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% — 'base' and 'quote' are bare strings with no format hints. The description partially compensates by showing examples (USD, EUR, GBP, JPY), which reveals the 3-letter ISO code convention and the base→quote direction, but never enumerates or points to the ~30 valid currencies, so an agent still cannot validate inputs.

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?

States a specific verb+resource: 'end-of-day FX rate between any two ... currencies', with concrete examples (USD to EUR, GBP to JPY). The 'end-of-day' qualifier and 'global' scope meaningfully separate it from sibling tools like global_fx_convert or global_fx_timeseries, though the distinction from the plain 'fx_rate' sibling is never made explicit.

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?

Usage is only implied: 'end-of-day' signals this is not a real-time quote, and tennis-court examples show the base/quote direction convention. No statement of when to prefer this over fx_rate, convert, or global_fx_convert, and no conditions under which it should not be used.

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