search_virustotal

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

Without annotations, the description provides key behavioral context: it is passive (read-only) public-source collection, auto-detects input type, and requires authorization. It does not detail rate limits or error handling, but the passive nature is well conveyed.

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 three sentences with no wasted words. It front-loads the purpose, then adds requirements and usage policy. Each sentence adds distinct 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?

Given the tool has only 2 parameters, no output schema, and no annotations, the description covers input types, requirements, and ethical boundaries. It could detail the expected output format better, but the json_output parameter helps. Overall, it is adequate for simplified selection.

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?

The description adds significant meaning to the 'target' parameter by listing acceptable input types (IP, domain, URL, file hash) and noting auto-detection. The 'json_output' parameter already has a schema description, but the description clarifies the tool's capabilities beyond the schema's sparse coverage (50%).

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 specifies the tool checks IP, domain, URL, or file hash against VirusTotal's 70+ antivirus engines and threat intelligence. It clearly states the action (check) and the resources (various input types), distinguishing it from sibling tools that focus on other data sources.

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 explicitly requires the VIRUSTOTAL_API_KEY environment variable and restricts use to authorized assets. It implies usage for threat intelligence, but does not explicitly state when not to use it versus siblings like search_ip or search_domain.

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