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

With no annotations, the description carries the full burden and does so richly: 404 for untracked tokens (not charged), 20s/30s refresh cadences with stale inputs refused via 503 (not charged), $0.03 USDC x402 cost, and a research-data disclaimer. These are exactly the operational traits an agent needs and that no schema field encodes.

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 outcome ('avoid, caution or ok') before the supporting machinery, and every clause carries a distinct fact (inputs, errors, freshness, cost, disclaimer). It is dense and long, but nothing is padding.

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?

An output schema exists, so return values need not be explained, and the description covers what remains: the decision inputs, not-charged error paths, staleness handling, pricing, and the non-advice disclaimer. An agent has everything needed to call it correctly and interpret failure modes.

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% for the single addr parameter and its description already specifies the 0x+40-hex format, so the schema does the heavy lifting. The description adds only the implicit context that the address is a Robinhood Chain token, which triggers the verdict lookup, so baseline 3 is appropriate.

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 verb+resource ('verdict' on a 'Robinhood Chain token') and the exact deliverable ('avoid, caution or ok, with every reason'). It names the concrete inputs it aggregates and is clearly distinguishable from sibling rh_token_rugcheck and rh_token_precall, which it consumes rather than duplicates.

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?

'One call before you buy a Robinhood Chain token' gives clear decision-point context, and the composition (rug check + pre-call + desk outcome) implicitly routes agents here instead of the component tools. It stops short of an explicit 'use this instead of rh_token_rugcheck' exclusion, so not quite a 5.

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