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

With no annotations the description carries the full behavioral burden. It usefully discloses the permissible date window, UTC day semantics, and the exact shape of what comes back (endpoint rates plus absolute and percent change), but it omits failure behavior (e.g. reversed dates), how non-trading days are resolved, and any auth or rate-limit context.

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?

A single tight sentence: the output content leads, followed by the validity window. No filler, no restatement of the name or title.

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 six-parameter read with no output schema, the description compensates by describing the returned fields and their meaning, and by stating the valid date range. It stops short of explaining how base_currency transforms the returned values or what happens on invalid or non-trading dates.

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 100% and each of the six parameters is documented inline, so the baseline is 3. The description adds real meaning beyond that by clarifying that date_from/date_to are inclusive endpoint days whose end-of-day rate is used, which the terse schema entries do not convey.

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 gives a specific verb and resource ('returns ... its rate at the end of date_from and of date_to and how much it changed') and even specifies the two output measures, absolute and percent. It implicitly separates itself from getRange/getHistorical by returning only the two endpoint rates plus a delta, but it never names a sibling, so the differentiation is inferred rather than stated.

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: an agent can infer this is the tool for 'how did X move between two dates'. There is no explicit when-to-use, when-not-to-use, or routing to getRange, getAverage, or getHistorical. The date-validity constraint (back to 1999-01-01, newest yesterday) is a boundary, not usage guidance.

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