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

Annotations already establish readOnly, idempotent, and closed-world behavior, so the safety profile is covered. The description adds genuinely non-structured operational context: it is a paid x402 call at $0.002 USDC per call on Base mainnet, and it discloses that the previous rate is only returned where the rate changed — a real data-shape caveat. Return cardinality/pagination is unmentioned but the tool is evidently a small fixed snapshot.

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?

Front-loaded with the resource and coverage list, then filter semantics, then price — every clause carries information (coverage, named institutions, return fields, filtering, cost). No filler and no restatement of the tool name as a sentence.

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 one-optional-param read-only lookup with no output schema, the description supplies everything needed to call it correctly: subject matter, geographic scope, filter mechanism and default, what fields come back, and the payment model. Nothing material is missing.

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 100% and the single parameter already documents the 2-letter ISO comma-separated format and the all-35 default. The description repeats the filter-by-ISO-code and default-of-35 facts rather than adding format examples or behavior for unknown codes, so the baseline of 3 applies.

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 and resource ('central bank policy interest rates') and pins down scope precisely: 35 countries in Asia and the Middle East, with named central banks (RBI repo rate, Bank Indonesia, SBP). It also declares the return contents (month of latest decision, previous rate where changed), so an agent can distinguish it from africa_central_bank_rates and the unrelated za_* siblings without opening either schema.

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 implied through scope: an agent can infer 'use this for Asian/Middle Eastern policy rates, filter by ISO country codes, default all 35'. However, there is no explicit when-to-use or when-not guidance and no routing to near-neighbors such as za_sarb_rates or exchange_rates, leaving region-vs-country disambiguation to inference.

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