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

Annotations cover only readOnly/openWorld, so the description adds real value: it discloses that missing evidence is explicitly marked 'unknown' (output convention), that latency is under a minute, and that the call costs 2.2 USDC on Base via x402 with a stated endpoint. That cost/payment disclosure is essential for a paid tool. Points are lost because a large share of the text is promotional identity/payout-wallet material rather than operational behavior.

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 purpose and input example are correctly front-loaded, but the second half is bloated with token-fee promotion, agent registry URLs, and payout-wallet addresses that do not help an agent decide or invoke. Roughly half the text could be removed without loss of operational 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?

With no output schema, the description must convey what comes back, and it does: the enumerated research facets plus the 'unknown' convention for missing evidence. Combined with the payment and latency notes, an agent has enough to call it correctly; only explicit sibling routing is absent.

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% with both parameters described, including the address pattern and chain enum, so the schema carries the semantics. The description adds only a concrete example object ({"chain":"base","contractAddress":"0x9401...8631"}), which is mildly useful but not additive beyond the structured fields. 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?

Opens with a specific verb+resource: what is publicly known about a contract address, enumerating the returned facets (project overview, social/transaction signals, risk summary, source URLs, observation time). It implicitly distinguishes itself from audit-style siblings by stating it is 'not a source-code audit', though it never names contract_security_scan or token_due_diligence directly.

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?

Provides an implied scope boundary ('Public-source research only: not a source-code audit or a guarantee of safety') and an example invocation, but gives no explicit when-to-use-vs-alternative routing among the many research/scan siblings (contract_security_scan, project_research_report, token_due_diligence). The agent must infer selection.

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