Order Book Summary (L4)

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

On top of the readOnly/idempotent/openWorld annotations, the description discloses that results are snapshot-derived, refreshed every 60s, latest-only with no history, that as_of_height is the L1 block of truth, and that age_s should be checked before citing. It also flags Pro-tier gating. The main omission is expected response shape, which is partly covered by the field enumeration.

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?

It is a long description but dense and front-loaded with the core question and the return enumeration before the caveats. Most sentences earn their place, though the coin-spelling warning is somewhat duplicative of the schema.

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-value burden and does so by naming the bands, imbalance metrics, and touch statistics an agent will actually receive. Combined with the freshness and interpretation guidance, an agent has everything needed to call and correctly cite it.

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 both parameters are already documented, including the case-sensitive coin spelling, the 404 on 'btc', and the spot-pair exclusion. The description largely restates this, adding the nuance that the value is 'passed through unchanged', which is marginal. Baseline 3 applies when the schema carries the detail.

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 opens with the exact question the tool answers ('how deep and how lopsided is this book right now?') and then enumerates the specific outputs: touch prices, spread in bps, per-side size/count/wallets in nested bands, imbalance, and post-only share. It explicitly distinguishes itself from the sibling 'market_orderbook' by labeling this the L4 view versus the aggregated L2 one.

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?

It gives a concrete worked example ('is HYPE's bid side thinner than its ask side inside 1 %?'), names the alternative tool and the condition that separates them (L4 vs L2), and states the refresh cadence and latest-only constraint so the agent knows when the answer is valid. Nothing about when to reach for this tool is left to inference.

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