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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description meaningfully enriches this by enumerating the five concrete verification layers (registry allow-list, Jupiter, Metaplex authority, liquidity, age+holder count) and defining the return envelope (four statuses, reasons, warnings, per-layer findings). This is exactly the additive context expected beyond the structured fields — just slightly short of perfect for not detailing behavior on optional inputs.

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?

Three sentences, each earning its place: purpose, mechanics, and instruction. The middle sentence is dense but well-organized — the list of layers and the parenthetical distinct-value enumeration make it scannable. Minor deduction for the long middle sentence arguably burying the return contract.

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 output schema covers the return shape and annotations cover the safety profile, so the description's remaining gap — the semantics of symbol and caller_id — is the sole incomplete piece. For a read-only verification tool, this is a complete-enough contract to guide correct invocation.

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?

With 0% schema coverage, the description bears full burden for parameter semantics. It strongly contextualizes token_address via the 'token mint' and 'unfamiliar token' framing, but symbol and caller_id are never mentioned — are they lookups, filters, or logging metadata? Given the 0% coverage baseline, the description should have compensated more fully.

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 states a specific verb+resource ('authenticity check for a token mint') and immediately disambiguates scope with '(read-only, no execution)'. It enumerates the five verification layers, making it instantly distinguishable from siblings like verify_transaction (transaction-level), token_info, or get_token_classification without opening schemas.

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 closing directive, 'Call this before swapping into an unfamiliar token,' is an explicit when-to-use instruction, and the tie-in to the swap/trade tool enforcement flow gives context on when the same logic is invoked. It doesn't name an alternative or explicitly state when not to use it, but the usage context is clear enough to route an agent 95% of the time.

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