IOC Lookup

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds behavioral details: auto-detection of type, per-type source coverage, verdict fields (sources_queried, sources_unavailable), and failure handling. No contradictions.

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?

Every sentence serves a purpose: purpose, source coverage, usage guidance, rate limits, output format. No filler, well-organized, and front-loaded with key 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?

Given the tool's complexity (multiple input types, multiple feeds, output schema exists), the description covers input possibilities, feed mapping, failure behavior, and output structure. It is fully informative for an agent to invoke correctly.

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 a detailed description of the indicator parameter. The description adds context about auto-detection and feed behavior, enriching the parameter semantics beyond the schema alone.

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 verb 'Enrich' and the resource 'Indicator of Compromise' with explicit types (IP/domain/URL/hash) and auto-detection. It distinguishes from siblings like threat_intel (domain-only) and hash_lookup (richer MalwareBazaar data), making the purpose clear and unique.

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?

Explicit guidance: 'Use as primary IOC triage tool when type unknown' and alternatives for specific cases. Rate limits (30/hr free, 500/hr Pro) are provided, helping the agent decide when to use this tool vs. others.

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