aegis

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

With no annotations provided, description carries full disclosure burden. It compensates adequately by detailing the return payload structure ('action patterns, targets, risk levels, and approval requirements'), giving the agent semantic context for what data to expect. Could improve by noting caching behavior or auth requirements, but the return value disclosure is the critical behavioral trait for a read operation.

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 highly efficient sentences with zero redundancy. First sentence establishes purpose immediately; second sentence adds return value semantics. Perfect front-loading with no filler.

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?

Appropriately complete for a zero-parameter read operation. Since output schema exists, the description appropriately summarizes rather than exhaustively documents return fields. Adequately scopes the domain (governance policy) but could reference sibling relationships explicitly.

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?

Zero parameters present (empty schema), establishing baseline 4 per scoring rules. No parameter guidance is needed or expected.

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?

Clear imperative verb 'Get' with specific resource 'governance policy rules'. Effectively distinguishes from sibling 'update_policy' (mutation) and evaluation siblings like 'evaluate_action' (action validation) by indicating this retrieves the configuration itself rather than assessing actions against it.

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?

Implies read-only usage appropriate for retrieving current configuration, but lacks explicit guidance on when to use this versus 'check_risk' or 'evaluate_action' (evaluation scenarios) versus 'update_policy' (modification scenarios). No prerequisites or context provided.

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