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

Against annotations that only declare readOnly/idempotent/openWorld, the description carries genuinely additive behavior: a per-call price ($0.002), the fact that bad input is rejected before any charge, the exact auth header format (Bearer p0k_…), a key-purchase URL, and how the paid-vs-unpaid path differs. This is exactly the cost and billing context annotations cannot express.

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 use case is front-loaded and the pricing/validation/auth facts each earn their place, but the single dense paragraph packs a long purchase URL and two distinct execution modes into one block, which makes it harder to parse. A short split between 'what it does' and 'how billing works' would improve scanability without adding words.

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?

Given no output schema, the description still tells the agent what comes back (rate, date, source), that a full schema link is available, and how to complete the fetch with an x402 or MPP client. The one gap is that it does not say what the returned document looks like in the paid-key path or whether the series/date echo back, but for a three-parameter read tool this is close to sufficient.

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%, so the schema already documents date, tenor, and series, including the default tenor of 10y and the enum meanings. The description only echoes the 10y default ('US Treasury par yield curve (default 10y)') and adds no format or edge-case guidance beyond what the schema states, which is the expected baseline 3 when the schema does the work.

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 names a specific resource set (SOFR from NY Fed, euro short-term rate from ECB, US Treasury par yield curve) and what is returned with it (date and source), which is far more concrete than the bare title 'Rates reference'. It is slightly blurred by the dual delivery modes ('returns the exact paid x402 request' vs. 'makes the paid call itself and returns the data'), so an agent must read the whole paragraph to know what it actually receives.

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 opening 'Use when an agent needs an official reference rate with its date and source' gives a clear selection condition, and the P0 access key clause explains the alternative execution path. No sibling tools among eu_fx, hazards_near, weather, or news_latest overlap in domain, so no cross-tool routing is needed, but the description never explicitly says so or contrasts with eu_fx for FX-adjacent needs.

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