rir_audit_org

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

Annotations establish read-only/idempotent safety; the description adds critical behavioral context not present in annotations: 6-hour caching policy, LACNIC RDAP limitation, and RDAP entity database sources. Could be improved by mentioning rate limits or authentication requirements, but coverage of data source limitations and caching is valuable.

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?

Well-structured with clear sections (overview, use cases, tips, args, returns). The use cases and tips earn their space by preventing misuse. The JSON return schema is somewhat verbose given that an output schema exists, but it ensures the LLM understands the structured string output. Front-loaded with the core action in the first sentence.

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?

Comprehensive for a complex aggregation tool spanning multiple external RIR databases. Documents return structure (including error field), notes the LACNIC limitation, explains partial matching behavior, and provides the JSON output schema. Complete enough that an agent can predict both success and failure modes.

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?

With schema description coverage at 0% (per context signals), the Args section compensates effectively by documenting both parameters with concrete examples ('GOOGL-ARIN', 'Cloudflare') and default values ('markdown'). The distinction between handles and partial name matching is clarified, adding necessary semantic context for successful invocation.

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 opens with a precise action ('Find all IP blocks and ASNs') and scope ('registered to an organization across all RIRs'). The 'across all RIRs' and 'organization-wide' framing clearly distinguishes this from siblings like rir_query_ip or rir_query_asn which handle single resources.

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 four specific use cases (M&A due diligence, security research, ICANN policy, incident response) that establish when to select this tool. Includes practical tips for query precision (org handles vs names) and caching behavior. Lacks explicit 'when not to use' contrast with single-resource lookup siblings, though the use cases imply the scope.

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