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

Beyond the readOnlyHint annotations, the description reveals how the tool handles insufficient liquidity: 'A size the book cannot absorb comes back as "filled": false with the amount that could actually be filled, never an extrapolated price.' It also explains the interpretation of slippage: 'The floor is half the spread; anything above it is the size eating through levels.' These are behavioral details not present in structured annotations.

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 bit longer than typical but each sentence serves a purpose: first sentence states the core function, second differentiates from siblings, subsequent sentences explain output and edge-case behavior. It is front-loaded with the most important information and the additional detail is justified for a tool with non-obvious behavior, though some editorializing ('This is the number that decides...') could be trimmed.

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 the complexity of the tool and the presence of a full output schema and annotations, the description provides crucial context not captured elsewhere: the venue comparison, behavior when the book cannot absorb size, and the interpretation of slippage as spread plus crossing levels. This makes the tool's behavior clear and complete for an agent to know when and how to invoke 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?

The schema already provides full descriptions for both coin and sizesUsd (100% coverage), so the tool description doesn't add parameter-level semantics beyond what the schema contains. It does reinforce that sizesUsd is 'per requested notional' but this matches the schema's 'Trade sizes to price, in US dollars.' Baseline of 3 is appropriate since the schema carries the parameter documentation burden.

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 the tool computes actual execution cost for a given trade size by walking live order books of Bybit and OKX. It explicitly distinguishes from siblings: 'Every other tool here reports where price is; this one reports the price YOU would get at YOUR size.' This is a specific verb+resource with clear sibling differentiation.

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 explicitly contrasts with sibling tools: 'Every other tool here reports where price is; this one reports the price YOU would get at YOUR size.' It also explains when the metric matters: 'This is the number that decides whether a correct thesis still makes money after costs.' This provides clear context for when to use the tool, even without naming specific alternatives.

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