scan_anti_analysis_primitives

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

With no annotations, the description carries full burden. It describes walking the string table, IAT, and section table, matching against a catalog, returning category-only labels without naming commercial products, and explicitly states what it does not check (byte-sequence evidence). This exceeds basic 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 moderately concise with a clear structure: purpose, scope, limitations, arguments, and return format. It is front-loaded with the main action. A few extra details (e.g., listing categories) are justified, but it could be slightly more streamlined.

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 no output schema, the description provides a detailed return format including fields like primitive, category, evidence_kind, offset, section, and by_category counts. It also mentions truncated. This covers the return value comprehensively 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?

Schema coverage is 0%, so description must compensate. It explains that max_per_category is a per-category cap with default 100, adding meaning beyond the schema. Path is self-explanatory for a file scan tool. While not exhaustive, it adds sufficient context.

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 clearly states it scans a binary for anti-analysis primitives, lists specific categories, and distinguishes from sibling tools like re-rizin.search_bytes and re-anti-analysis. The verb 'scan' and resource 'binary for anti-analysis primitives' are specific and unambiguous.

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 explains when to use this tool by noting that byte-sequence evidence requires a disasm pass via re-rizin.search_bytes, and that re-anti-analysis is the cross-tool orchestrator. It provides context for alternatives, though it does not explicitly list negative conditions for use.

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