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

Adds substantial context beyond the annotations: a hard rate limit of 3 calls/day per client, sample output on empty arguments, named upstream sources (GoPlus, honeypot.is, RugCheck, DexScreener), and a fail-closed policy mapping missing data to UNKNOWN. The safety profile itself is already carried by readOnlyHint/idempotentHint, and it does not describe latency or quota-exhaustion error behavior, so it stops short of a 5.

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 free-tier constraint and quota are front-loaded where they matter most, and the signal list is compact despite being long. The mid-sentence 'Same output as the paid tool' is slightly out of place, but the whole description carries dense, non-redundant information.

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 read-only screening tool with no output schema, the description supplies the decision space (OK/CAUTION/AVOID/UNKNOWN), the data provenance, and the failure mode, which is enough to interpret results correctly. It omits any indication of response shape beyond the verdict label and does not explain what a quota-exceeded response looks like.

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 both parameters are already documented and the baseline is 3. The description's statement that 'empty arguments return a sample check' does add behavioral meaning about token, but it also sits awkwardly against the schema marking token as required, leaving an agent to infer that omitting it is legal.

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 — a pre-trade token/memecoin verdict for EVM and Solana — plus the concrete signals checked (honeypot simulation, taxes, mint/freeze authority, liquidity, pair age). It also immediately distinguishes itself from the paid sibling 'token-check' as the free, rate-limited tier, so an agent can tell the two apart without opening either schema.

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?

Clear on the situation it serves (pre-trade risk screening) and on the constraint that governs selection: 3 calls/day per client, no payment, same output as the paid tool. It does not explicitly say 'switch to token-check when the free quota is exhausted', so the escalation path is implied rather than stated.

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