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

Annotations already indicate readOnlyHint=true and openWorldHint=true. The description goes beyond by explaining it does not store history ('Gak nyimpen histori -- snapshot sesaat'), defines the wall detection heuristic (2x median), and notes single-venue walls are more prone to spoofing. It also mentions symbol auto-mapping across exchanges. These details add behavioral context not present in annotations, making the tool's runtime behavior clearer without contradicting the read-only and open-world hints.

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, dense sentence that front-loads the main action (snapshot real-time orderbook across exchanges) and then specifies the analysis logic and caveats. There is no wasted wording, though it is packed with multiple clauses. It remains focused and readable, earning a high score for conciseness without being terse.

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 no output schema, the description explains the core output categories (cross-venue vs single-venue walls) and references docs/tool_response_reference.md for the 'full' detail format. It doesn't explicitly outline the return structure, but it provides enough for an agent to understand what the tool does and how results are categorized. For a moderately complex multi-exchange analysis tool, this is reasonably complete, though an explicit output description would bump it to 5.

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 both parameters (symbol, detail) fully described. The description adds the crucial detail that symbol is in Binance format (BTCUSDT) and auto-mapped to other exchanges, which is not in the schema. It also reinforces the token-saving behavior of the 'summary' detail. This is a small but valuable addition beyond the schema, so the baseline of 3 is raised to 4.

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 it takes a real-time orderbook snapshot across Binance/Bybit/OKX, detects large walls (qty >= 2x median), and classifies them as cross-venue corroborated vs single-venue. The verb 'Snapshot' and specific resource (orderbook across three exchanges) make the purpose unambiguous. It also differentiates from siblings like binance_get_order_book_depth (single exchange) and whalescope_compare_funding_across_exchanges (funding, not orderbooks).

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 implies usage for cross-exchange orderbook wall analysis and notes it's a momentary snapshot (no history), suggesting real-time use. However, it does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or conditions for choosing it over binance_get_order_book_depth or whalescope_compare_funding_across_exchanges. The 'detail' parameter gives some guidance (summary saves tokens) but that's parameter-level, not tool-level.

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