extract_iocs

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

No annotations are provided, so the description carries the full burden. It discloses meaningful behaviors: defanged input is refanged first, filenames are not mistaken for domains, and output is sectioned/defanged. This exceeds a minimal 'extracts IOCs' statement. Missing details like output structure or size limits, but the core behavioral traits are transparent.

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?

Three sentences with no filler. The main purpose is front-loaded, the UIOC types are enumerated compactly, and the edge case about filenames is a useful one-liner. Every sentence adds 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?

For a simple 2-parameter tool with no output schema, the description explains input types, output sections, defanging/refanging behavior, and an edge case. It does not specify the exact return structure or field names, which would help an agent parse results, but the lack of an output schema lowers that burden slightly. Overall, it is nearly complete for its 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?

Schema description coverage is 50%: 'defanged' is described, 'text' is not. The description compensates for the 'text' parameter by specifying valid inputs (reports, alerts, email) and mentions defanging behavior, but it never explicitly names the 'defanged' parameter or its default. It adds some semantic value beyond the schema but does not fully bridge the coverage gap.

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 uses a specific verb ('Pull every indicator out of a blob of text') and resource, enumerates supported IOCs, and states the output treatment (sectioned and defanged). It clearly differentiates from sibling tools like defang_text by adding extraction + refanging behavior. No ambiguity about what the tool does.

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?

It implies the use case ('a report, an alert, a mail — and return them sectioned and defanged, ready for a ticket') and that defanged input is handled. However, it never explicitly contrasts alternatives like defang_text or identify_hash, so an agent might not know when to choose this tool over a sibling. Usage context is present but exclusions are absent.

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