get_decision_history

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

Annotations already declare readOnlyHint=true and destructiveHint=false. Description adds 'audit trail' implying immutable historical records, and 'complete' suggesting no filtering. However, it omits pagination behavior, chronological ordering, or whether this includes system-generated vs user-logged decisions despite openWorldHint=true.

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?

Single sentence, front-loaded with active verb, zero redundancy. Appropriate length for a simple single-parameter read operation.

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?

Minimally sufficient for a low-complexity read tool with rich annotations. However, gaps remain: 'complete' is undefined (time range? all decision types?), and without output schema, some hint about returned structure (array of decisions?) would improve invocation confidence.

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 ideaId fully documented. Description mentions 'for an idea' which aligns with the parameter but adds no additional semantic constraints (e.g., UUID format, validation rules) or usage context beyond the schema.

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 verb 'Get' with specific resource 'decision history (audit trail)' and scope 'complete...for an idea'. The parenthetical clarification distinguishes this from generic idea retrieval, though it doesn't explicitly differentiate from sibling get_idea.

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 on when to use this versus get_idea (current state) or log_decision (writing decisions). No mention of prerequisites like idea existence or permissions needed to view audit trails.

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