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

With no annotations, the description carries the full burden and does substantial work: it discloses that the verdict is rule-based (implying deterministic, non-LLM output), enumerates the verdict values, the 0-100 score range, and the language options. It omits auth needs, rate limits, and any latency/caching behavior, which keeps it out of 5 territory.

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 purpose, then packed with operational detail in a single dense paragraph; nearly every clause carries new information. The nested parentheticals make it slightly harder to parse than ideal, but there is little waste.

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?

With no output schema and no annotations, the description correctly covers the return shape (verdict, risk score, findings, naira value, message red flags) and the input surface. The only real gap is the unexplained `amount_ngn` parameter and the absence of any note on limits or failure modes for unresolvable input.

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 0%, so the description must compensate, and it does for three of four parameters: `text` (accepted input formats), `chain` ("auto" detection plus DexScreener chain ids like ton/sui/tron/hyperevm, 64 networks), and `lang` (en or pcm). `amount_ngn` is only implied by "what you'd get back in naira" and never explicitly tied to the parameter name.

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 and resource (check a crypto token for scam risk before buying) and enumerates the accepted input forms: contract address, DexScreener/pump.fun link, or forwarded message. This is clearly distinguishable from siblings like scan_message or token_history, which serve different scopes.

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?

Gives a clear usage context ("before buying") and broad input acceptance across 64 networks, but never names an alternative or an exclusion. It doesn't tell the agent when to prefer scan_message or explain_finding over this tool, even though a forwarded message could plausibly go to either.

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