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

With no annotations, the description carries the full burden and does so unusually well: it defines per-rate status semantics (ok/stale/pending/unsupported), retry timing, the 7-day dynamic-coin expiry, uid churn after reset, payload sizing, and how an optional source never falls back to another source's price. Only auth/permission context is absent, which is minor for a read-style pricing call.

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-loads purpose and endpoint before the detail, and nearly every sentence carries operational information. It is nonetheless dense to the point of sprawl, with a slightly redundant parenthetical about the dual text/structuredContent payload and some overlap with the schema's own source description.

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?

An output schema exists, so return rendering need not be covered, yet the description still explains the meaningful response semantics (status values, decimal-string prices, size). Combined with limit and expiry behavior, an agent has everything needed to call this 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 the baseline is 3, and the description earns above that by explaining the class-ranged uid encoding (uid = class*1e8+seq with concrete examples), the per-source 'unsupported rather than substitute' rule, and the size cost of include=sparkline. Most of this meaning is genuinely additive rather than restating the schema.

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?

Opens with a specific verb+resource+endpoint: "Batch indicative prices for catalog uids (POST /v1/rates)." It also differentiates from siblings by routing uid discovery to search_assets and limits to get_meta, so the agent can place it in the toolset without reading other schemas.

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?

Gives concrete when-to-use guidance: use search_assets to find uids, request sparkline "only when needed," consult get_meta for limits, and read ratehub://docs/behavior for edge cases. It lacks explicit when-not-to-use or routing against the historical sibling get_series, so it stops short of a 5.

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