Order book depth

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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds a real caveat the annotations don't: data 'may be delayed or wrong', which matters for trading-adjacent reads. No disclosure of rate limits, ordering, or whether the book is a snapshot, so not a 5.

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 core sentence is dense and front-loaded, but roughly half the text is legal boilerplate ('Education/information only; not financial advice') that does not help an agent decide or invoke. Trimmable without losing invocation-relevant information.

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 carries the return-shape burden and does reasonably: price levels per side plus cumulative base/quote liquidity. It stops short of saying whether mid price and the band boundaries are echoed in the response, or how levels are ordered.

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 baseline is 3; the description still adds value by explaining that within_pct yields cumulative base quantity and quote notional near mid – semantics the schema only hints at with 'Depth bands as % distance from mid'. It also restates 'top N levels per side' for levels, reinforcing the per-side unit.

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?

Names a specific resource (DeepBook pool order book) and a precise scope: top N price levels per side plus cumulative liquidity within ±X% of mid. An agent can separate it from get_mid_price (single mid) and get_volume (aggregate volume) without opening the 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 by 'order book depth' – depth/liquidity inspection – but the description never states when to prefer this over get_volume, get_pool_stats, or get_mid_price, nor any exclusions. Context ('read-only public data') is present but no routing guidance.

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