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

Annotations only cover readOnlyHint and openWorldHint; the description adds the data source (Blockscout), the lookback window (most recent 50 transactions), an explicit false-negative disclosure, the output signal name (POSSIBLE_CLUSTER), and the full payment model including the x402 chains and the fact that failed calls are free. That is substantial behavior beyond the structured fields.

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 carrying distinct load: capability and method, limitations, then pricing. The key scope constraint is front-loaded before the caveats. No filler and no restatement of the title.

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 enumerated, and the description still names the headline signal. For a paid, single-parameter, read-only forensic check, an agent has everything it needs: input format, data source, known blind spots, cost, and payment mechanism.

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% and the single parameter already documents '2 to 10 Ethereum addresses separated by commas,' so the description adds no format, ordering, or validation detail beyond the schema. The mention of shared counterparties clarifies what the wallets are compared on, but that is output semantics rather than parameter semantics. Baseline 3 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 states a specific verb and resource (checks 2-10 Ethereum wallets for shared counterparties) and defines exactly what a counterparty is: an address several wallets sent to or received from in their last 50 transactions. That is enough to distinguish it from a generic profiler, but it never names the close siblings (holder_cluster_analyzer, wallet_forensic_profiler, deployer_rug_forensics), so the agent must infer the boundary itself.

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 applicability conditions (2-10 wallets) and, unusually, states when the tool will underperform: 'recent-page only, no funding-source trace, so it finds some clusters and misses others.' That is real guidance about when not to rely on the result. It stops short of routing the agent to an alternative tool for the cases it misses, which keeps it below 5.

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