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

Annotations declare readOnly, idempotent, openWorld, and non-destructive. The description adds significant behavioral traits: deterministic, no keys required, ~1.5s cache, per-call cost ($0.05 via x402), and auto-fallback mechanism. This goes well beyond the annotations.

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 description is a single, well-structured paragraph that front-loads the purpose, then lists key features, behavioral properties, and an example. Every sentence adds value, and there is no redundancy or fluff.

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 the tool's low complexity (3 parameters, simple output), the description covers all essential aspects: purpose, return values (bids/asks, mid, spread, liquidity, slippage), caching, cost, auth, and source behavior. The output schema exists, so return value details are not required.

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% with descriptions for all three parameters. The description adds further meaning by explaining the source auto-fallback, normalizing across exchanges, and providing an example usage string. It clarifies the depth range (1-200) and default (50) implicitly.

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 clearly states the tool retrieves L2 order-book depth for crypto pairs, including bid/ask ladder and analytics. It specifies the verb 'get' and the resource 'orderbook', distinguishing it from sibling tools that perform other data retrieval or actions.

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 description provides clear context: it's for crypto pairs, normalizes across exchanges, and offers auto-fallback or specific source selection. It does not explicitly state when not to use it or mention alternatives, but the context is sufficient for appropriate selection among sibling tools.

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