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

With no annotations, the description carries the full behavioral burden. It does disclose that this is research rather than an order, which is useful, but it omits what output the agent should expect, whether it performs any writes, and what data sources or limitations apply.

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 short, front-loaded with the core subject, and every sentence adds color or constraint. The informal jargon is vivid but sacrifices a little clarity.

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?

The tool has only one parameter and no output schema, yet the description still does not say what the research result looks like or how to interpret the findings. An agent can call it with an address but not anticipate the return value.

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 fully documents the lone 'address' parameter as a Token 0x on Robinhood Chain. The description adds no new parameter-level semantics, so the baseline score applies.

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 identifies a specific on-chain research target: Pons tax-exempt snipe clusters and fake-activity boosts. 'Research, not an order' provides actionable verb-like framing, distinguishing it from execution tools.

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 clear context: use this tool when investigating suspicious on-chain clustering and fake activity, and explicitly says not to treat it as an order. However, it does not name alternatives or state when to prefer another talon_* tool.

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