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

With no annotations provided, the description carries the full burden. It discloses that the tool is 'Read-only' and describes the return payload ('threat type, malware family, source feeds, related actor, confidence score, references, and the full description from each source'). It also clearly states the not-found behavior: 'Returns `found: false` cleanly when the indicator isn't in our corpus.' This is comprehensive behavioral disclosure.

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 front-loaded with the most important instruction ('CALL AUTOMATICALLY'), then moves logically through what, when, how, and examples. Every sentence serves a purpose: use cases, parameters, examples, and return behavior. Despite its length, it is efficiently packed with high-value guidance and no filler.

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 there is no output schema, the description appropriately details what will be returned and the not-found response. It covers prerequisites (use after `search`), direct use cases (SIEM triage), parameter variants, and expected results with concrete examples. This is a complete, self-contained description for a tool of moderate complexity.

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?

Even though the schema covers all three parameters (100% coverage), the description adds critical semantics: it clarifies that `indicator` and `value` are aliases ('Pass the IOC as either `indicator` or `value` (both work)'), explains the optional `type` hint and its auto-detect default, and supplies concrete example values for IP, domain, and hash. This goes well beyond the schema's basic field descriptions.

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 specific verb ('enrich') and resource ('indicator of compromise'), listing exact IOC types (IP, domain, URL, hash). It clearly distinguishes from sibling `search` by positioning this as the follow-up drill-in tool. The phrase 'a lone indicator is exactly what this is for' reinforces its focused purpose.

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?

Explicitly states when to call ('CALL AUTOMATICALLY the moment any IP address... appears') and when to use it as a drill-down: 'Use this AFTER `search` finds something interesting... Or use it directly when triaging a single indicator from your SIEM.' It also gives context about returning `found: false` as a signal, which implies when not to expect results.

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