audit_sybil_risk

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld). The description adds deployment metadata — capability status, tier gating, mock_supported false — which is genuinely useful for knowing whether it is callable and whether mocks work, plus the batch limit and a rough return shape. It stops short of describing cost, latency or how the risk score is derived, so it is additive but not rich.

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 core sentence is tight and front-loads the purpose reasonably. However, the bracketed preamble of capability/tier/mock flags and two raw API routes consumes roughly half the text with metadata of limited selection value.

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, the description does supply return values (cluster risk score plus hygiene suggestions) and annotation coverage handles safety. What is missing — failure behaviour on malformed addresses, whether tier gating can make the call unavailable at runtime — is secondary for a read-only audit.

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?

There is one parameter at 0% schema description coverage, but the description does restate the 1-10 count bound, which is otherwise only in minItems/maxItems. It never explains address format requirements or how the addresses are grouped/scored, so meaning beyond the schema is thin — adequate but not compensating for the coverage gap.

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 gives a specific verb and resource — 'audit 1-10 EVM addresses for sybil risk' — and states the outputs (cluster risk score, hygiene suggestions). This separates it from near-neighbours like audit_allowance_risk, simulate_transaction_risk and run_risk_sentinel by domain, though no sibling is named explicitly.

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 says nothing about when to reach for this tool versus audit_allowance_risk, simulate_transaction_risk or the broader run_risk_sentinel. The 'Research:' prefix hints at exploratory use but gives no preconditions, no exclusions, and no pointer to an alternative.

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