Get Tool Intelligence

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint, establishing safe, read-only behavior. The description adds detail on return fields (class, prevalence, etc.), which is valuable context beyond annotations. No behavioral contradictions.

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?

A single, well-structured sentence that front-loads the core action (pivot on a tool name) and efficiently lists the return values. No unnecessary words.

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?

Despite lacking an output schema, the description completely explains what the tool returns: canonical tool + class, prevalence, threats/actors, and ATT&CK techniques. Combined with annotations covering safety, the description provides sufficient contextual completeness.

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 100%, so the baseline is 3. The description adds meaning by categorizing the name as offensive tool/utility/RMM/LOLBin and providing concrete examples (Cobalt Strike, Mimikatz, AnyDesk, PsExec), enhancing the agent's understanding of valid inputs.

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 the tool's function: pivoting on an offensive tool/utility/RMM/LOLBin by name, and lists the returned information (canonical tool, class, prevalence, threats, actors, ATT&CK techniques). Examples (Cobalt Strike, Mimikatz) solidify understanding. It distinguishes from siblings like get_malware_intelligence which focuses on malware, not tools.

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 implies when to use: when you have a known tool name. It provides examples of valid inputs. However, it does not explicitly state when not to use or mention alternatives among siblings, though the context is clear.

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