aegis

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

Since no annotations are present, the description carries the full disclosure burden. It successfully documents the three possible return decisions (auto, approve, block) and their meanings. However, it omits critical behavioral traits like whether the evaluation creates an audit log (write side effects), latency characteristics, or error conditions when no policy exists.

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 front-loaded with purpose and return values. The structured 'Args' block is efficiently organized despite the schema's lack of descriptions. While the indentation is irregular, every sentence delivers value with minimal redundancy.

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 description covers the input parameters adequately and mentions return values despite the presence of an output schema. However, it fails to contextualize the tool within the governance suite—missing references to 'evaluate_batch' for bulk operations or how it relates to 'check_risk'.

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?

With 0% schema description coverage, the description compensates effectively via the 'Args' block, providing human-readable definitions for all five parameters including helpful examples for 'action_type' and 'target'. It clarifies optionality for 'description' and 'agent_id' and explains the arbitrary structure of 'params'.

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 evaluates an AI agent action against governance policy using specific verb-object phrasing ('Evaluate... action'). However, it does not explicitly distinguish this from sibling 'check_risk' or clarify when to use 'evaluate_batch' versus this single-action variant.

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?

No guidance is provided on when to invoke this tool versus alternatives like 'check_risk' or 'evaluate_batch'. There are no stated prerequisites, conditions, or exclusion criteria (e.g., 'use this when policy evaluation is needed' or 'do not use for bulk operations').

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