Tool Intelligence

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds value by revealing that the tool normalizes arbitrary tool names to a canonical form ("Returns the canonical tool"), which is useful behavioral context about name resolution. However, it doesn't disclose pagination, result limits for prolific tools, or edge cases in name matching. With annotations covering safety, a 3 is appropriate.

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, dense sentence that front-loads the purpose and lists examples inline, then enumerates all four return-value dimensions. Zero wasted words, no disconnected digressions, and the return payload description is packed efficiently.

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?

The tool is a simple single-parameter lookup with full schema coverage and an output schema present, so the bar is lower. The description fully specifies what data the returns include (canonical tool, class, prevalence, threats/actors, ATT&CK techniques), which is comprehensive for a read-only intelligence lookup. Slight gap: no mention of matched-tool disambiguation or tool obfuscation/misspelling handling, but this is adequately covered for a simple pivot tool.

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% (the single 'name' parameter is documented with example values). The description reinforces the parameter semantics by giving more concrete examples and clarifying that arbitrary aliases get canonicalized. Baseline 3 is correct when the schema fully documents the only parameter and the description adds modest context around name normalization.

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 ("Pivot on") with a clearly defined resource type (offensive tool/utility/RMM/LOLBin by name) and lists concrete examples (Cobalt Strike, Mimikatz, AnyDesk, PsExec). It specifies exactly what the tool returns: canonical tool+class, prevalence, threats/actors, and common ATT&CK techniques, distinguishing it from intelligence tools on other entities like get_cve_intelligence, get_malware_intelligence, or get_actor_intelligence.

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 clearly establishes the input domain (offensive tool names, with concrete examples) and the lookup semantics (canonical name resolution). It sets implicit context for when to use this vs sibling intelligence tools for other entities (threats, CVEs, actors, malware). It doesn't explicitly state when NOT to use it or name exact alternatives, but the entity-type distinction is inferable from sibling names.

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