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

Goes well beyond the annotations by disclosing the exact cost model ('SPENDS 1 request of your monthly quota per call'), that the charge applies even on post-auth failure, that the call is never retried, and the plan prerequisite (Basic or higher). It also notes the response contains the result and the quote used.

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?

Quota cost is front-loaded, followed by purpose, plan requirement and endpoint. Every sentence carries signal, though the trailing 'GET /convert' adds little for an agent.

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?

With no output schema, the description still names the return contents ('the result and the quote used'), and it covers cost, billing failure semantics, plan gating and rate-mode selection. An agent has everything needed to invoke it correctly.

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%, so from/to/amount limits are already documented in the schema. The description only adds the semantic of the optional date parameter (historical vs real-time) and the output meaning, which is genuine but minimal added value over structured data.

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 concrete verb and resource ('Convert an amount from one currency to another') plus the two rate modes (real-time or a past date). It is clearly distinguishable from the rate-fetching siblings by operating on an amount rather than returning a quote table, though no sibling is named explicitly.

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?

'with real-time rates, or with the rates of a past date' tells the agent which mode the optional date parameter selects. It doesn't explicitly say when to prefer get_live_rates or get_historical_rates over converting, so routing to alternatives is only implied.

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