odei_smart_contract_audit

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It describes what the tool does (analyzes for security risks, returns a risk score and findings) and mentions performance aspects ('slower, more thorough' for 'check_holders'), which adds useful context. However, it lacks details on permissions, rate limits, error handling, or what 'actionable findings' entail, leaving gaps for a mutation-like analysis tool.

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 description is appropriately sized and front-loaded, starting with the core purpose and key features. Each sentence adds value: the first defines the action and scope, the second details analysis components and output, and the third specifies supported chains. There is no wasted text, though it could be slightly more structured (e.g., bullet points for clarity).

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?

Given the tool's complexity (security analysis with 3 parameters) and no annotations or output schema, the description is moderately complete. It covers the purpose, analysis types, and output format (risk score and findings), but lacks details on behavioral traits like authentication needs, rate limits, or error cases. For a tool with no structured output, more elaboration on return values would be beneficial, though the description provides a basic framework.

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 description coverage is 100%, so the schema already documents all parameters ('address', 'chain', 'check_holders') with descriptions and constraints. The description adds minimal value beyond the schema, mentioning 'Supports Base and Ethereum contracts' which aligns with the 'chain' enum, and implies 'check_holders' affects thoroughness. Baseline 3 is appropriate as the schema does the heavy lifting, but the description does not add significant semantic depth.

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 clearly states the specific action ('Analyze an EVM smart contract address for security risks') and resource ('smart contract'), distinguishing it from siblings like 'odei_guardrail_check' or 'odei_world_model_query' by focusing on security auditing rather than general checks or queries. It specifies the scope (EVM contracts on Base and Ethereum) and the analysis components (verification status, vulnerability patterns, token safety, knowledge graph cross-referencing).

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 description provides clear context for when to use this tool: for security risk analysis of EVM smart contracts on Base or Ethereum. It implies usage by specifying the supported chains and analysis types, but does not explicitly state when not to use it or name alternatives among the sibling tools (e.g., 'odei_guardrail_check' might be for different checks). The guidance is sufficient but lacks explicit exclusions or comparisons.

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