arai_recent_decisions

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

No annotations provided, so description carries full burden. It discloses output fields (tool, decision, rule, source file) and notes the default time window. Does not mention side effects or safety, but read-only nature is implied. Adds value beyond schema by explaining the feedback loop closure.

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?

Concise, front-loaded with the primary action, then usage guidance, then output details. Every sentence adds value; no redundant or ambiguous phrasing.

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?

No output schema, but the description explains the return data comprehensively (tool, decision, rule, source). Covers the use case, parameters, and output. The tool is simple (0 required params) and the description is fully adequate.

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% with descriptions for all three parameters. The description adds examples for 'since' ('1h', '24h') and rationale for defaults ('stale entries don't crowd out today's'), going beyond the schema's bare specifications.

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 it looks up recent guardrail decisions, with a specific verb ('look up') and resource ('guardrail decisions Ārai has emitted'). It distinguishes from siblings by focusing on past decisions, unlike 'arai_check_action' (checking an action) or 'arai_add_guard' (adding a rule).

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?

Explicitly states when to use: 'when you've just been denied or warned and want to check whether you've hit the same rule before.' Provides context for session_id and since defaults, but does not explicitly mention when not to use or list alternatives.

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