Spot order book depth: walls and 2% depth from every spot venue on the coverage page

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

Annotations only declare read-only and open-world; the description goes well beyond by specifying the bucketing scheme (0.1% bins within 20% of mid, USD notional), the fixed coin universe, and the important caveat that uncorroborated books are returned with in_aggregate=false and held_out but excluded from aggregates. That held-out behavior is exactly the kind of non-obvious trait an agent must know before quoting numbers.

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-loaded with the triggering conditions before the payload description, so the most decision-relevant content comes first. It is dense and runs as one long block, which makes it slightly harder to scan, but essentially every clause (bucket size, coin list, held_out rule) carries operational value.

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?

No output schema exists, yet the description fully characterizes the return payload (binned book, walls with venue split, 2% depth, book reach, optional history) and the per-venue exclusion flag. For a two-parameter read-only tool, nothing an agent needs to call it or interpret results is missing.

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% and both params are self-documented, so the baseline is 3. The description adds real meaning by enumerating the supported coins (BTC, ETH, SOL, XRP, DOGE, ADA, LINK, AVAX, LTC, BNB) – information the schema only implies via a regex pattern – and by clarifying that hours enables the optional 5-minute summed history.

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 resource (spot order book depth across all venues on the coverage page) and enumerates exactly what it yields: 0.1% binned book, largest walls with venue split, 2% depth and book reach. This is clearly separable from siblings like get_liqmap, get_market_profile or get_slippage 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?

Gives four concrete user-question triggers ('where are the bid or ask walls', 'how deep is the book', 'buyers or sellers have more resting orders', 'order book heatmap'), which is strong positive routing. It stops short of naming an alternative tool or stating when not to use it (e.g. perp books vs spot), so it does not reach a 5.

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