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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds meaningful context about privacy: the server never requests the user's sample/analysis and instructs keeping them local, which is beyond annotations. It also clarifies the output structure (primary frameworks plus optional sibling frames). No contradiction with annotations.

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 compact, with the purpose front-loaded in the first sentence. The second sentence covers parameter usage, and the third adds privacy guidance—each sentence serves a distinct purpose without redundancy. It balances brevity with necessary details.

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 one-parameter read tool with no output schema, the description adequately explains what is returned (primary and optional sibling frameworks), how to control siblings, and data-handling expectations. It also ties the tool to the brief generation workflow, making its role clear despite not detailing the exact response structure.

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 already documents include_siblings with full coverage. The description adds practical meaning by explaining the effect of setting it to false ('skip sibling blocks') and by describing what sibling frames are (adjacent frameworks with whyOmitted notes). This goes beyond the schema's basic boolean description.

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 retrieves Lenny Zeltser's Malware frameworks, explicitly distinguishing primary frameworks from optional sibling frames. It names the specific resource and verb (get), and the mention of 'primary frameworks the brief structurally derives from' differentiates it from domain-specific sibling tools like assessment_get_frameworks or cti_get_frameworks.

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 clear context that this is for malware briefs and explains how to control sibling inclusion with the include_siblings parameter. It also notes that the server never requests samples or indicators, guiding the AI on privacy handling. However, it doesn't explicitly state alternatives or when not to use this tool versus other framework tools.

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