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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description usefully adds the on-chain source and return shape (bids/asks [price, qty]), but the non-custodial/keys/unsigned-tx boilerplate is nearly meaningless for a read tool and does not add behavioral insight.

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 first clause is well front-loaded, but roughly half the text is compliance boilerplate ('Non-custodial... never sees or holds keys...', 'Education only, not financial advice') that does not help an agent select or invoke this tool.

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?

Return format is stated, which compensates for the absent output schema, but one of two parameters (ticks) is unexplained and the boilerplate crowds out real gaps. Adequate but with clear omissions for a 2-param tool.

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 only 50%: 'pool' is documented but 'ticks' (default 10, range 1-50) has no schema description and the description never explains it. 'Around mid' vaguely implies depth levels, but the depth-count parameter and its bounds are left undocumented in both places.

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+resource+scope: 'Level-2 depth around mid read on chain from a DeepBook v3 pool (bids/asks [price, qty])'. An agent knows exactly what data comes back. However, it does not differentiate itself from the sibling get_order_book, which sounds like the same capability, so it falls short of a 5.

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?

No when-to-use guidance, no mention of when to prefer get_order_book, get_mid_price, or get_pool_stats instead. The only conditions given ('Spot only, no leverage', 'Education only') are product disclaimers, not invocation guidance.

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