Attribution Evidence

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which broadly cover the safety profile. The description adds meaningful value beyond annotations by disclosing the distinct `state` field semantics and the fact that this tool reveals attribution depth (researched vs intake stub) — genuinely useful behavioral context about what the returned data represents.

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?

Two sentences, zero waste. The first sentence enumerates the data fields returned; the second delivers the crucial differentiator (`state` and what it means). Every clause earns its place, and the example format mention adds concrete 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?

With a single required parameter, a high-coverage schema, full annotations, and an output schema present, most of the burden is already handled structurally. The description covers the key addition (state field semantics). It's a complete description for a focused, single-parameter lookup tool, though it could mention the output format/pagination slightly.

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% and the description clearly explains what the returned data will contain, which helps the agent understand what it's getting. The single parameter threat_id is fully documented in the schema with an example. With full schema coverage and one simple parameter, the description adds no additional parameter semantics needed beyond what's already provided, warranting the baseline 3.

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 this tool returns the attribution evidence for a threat: verdict, canonical actor, confidence, scope, evidence chain, signals, alternatives, and analyst reasoning. It explicitly distinguishes its purpose from siblings like get_threat by highlighting that it reports `state` (researched vs unresearched intake stub) which threats.threat_actor alone cannot convey.

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 that this tool reveals whether an attribution is a researched assessment or an unresearched stub — useful context for when to trust the output. However, it doesn't explicitly name when-not-to-use or point to alternative tools for getting the threat actor, leaving the when/alternative guidance implicit rather than explicit.

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