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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context beyond that: it reveals the paid nature ($0.45–$0.60 per call) and the three operational modes. It does not contradict the annotations and provides useful cost/usage awareness.

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?

Two sentences, front-loaded with the core purpose, followed by the cost note and pointer to alternatives. Every clause earns its place — no fluff, no repetition. The structure is ideal for quick AI parsing.

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?

For a moderately complex tool with 3 modes, 4 parameters, and no output schema, the description covers the essential usage context: three distinct actions, chain/timeframe defaults via schema, and pricing. It does not describe return values, but the modes imply what the output will be. This is adequate given the schema's completeness.

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 the schema already documents all parameters. The description adds a little semantic flavor by explaining what 'mempool' and 'protection' modes do, which maps to the 'kind' parameter. However, it does not introduce any additional parameter-specific details beyond the schema, keeping the baseline at 3.

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 a specific verb-resource pair ('Detect sandwich attacks and MEV extraction against a token or wallet'), then expands to cover the two additional modes (live mempool watch, protected routing recommendation). This clearly distinguishes it from sibling tools like analyze_token_security or check_token_safety, which focus on different security aspects.

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 mentions when to use the tool for detecting historical MEV, watching the live mempool, or getting routing recommendations. It also points to free alternatives via list_einstein_capabilities, providing a clear exclusionary condition. It could be more explicit about when not to use it, but the context is sufficient.

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