explain_last_curation

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

No annotations are provided. The description does not explicitly state that the tool is read-only or has no side effects, but it describes the output in detail (candidates, selections, reasons, token usage). For a read-only explanation tool, this is adequate but leaves some ambiguity about mutability.

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 two concise sentences: the first states the main function, the second adds detail and a use case. It is front-loaded with no extraneous information.

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?

Given no output schema, the description adequately explains the return content (candidates, selection status, reasons, token usage). Parameters are mostly covered, and the use case is clear. Minor omission: doesn't specify if the tool queries stored data or triggers a new analysis.

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 50%: 'optimization_id' has a clear description; 'lookback_days' is only described via constraints. The tool description explains the main purpose but does not elaborate on 'lookback_days' beyond the schema, so it partially compensates for the coverage gap.

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 renders a human-readable explanation of curation decisions, specifying the resource (Context Curator's decisions for an optimization) and action (render explanation). It distinguishes from siblings like 'get_trace' or 'inspect_context' by focusing on curation decisions.

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 provides a clear scenario: 'Use this when an output felt off and you want to understand which grounding sources the engine chose.' It implies a debugging use case but does not explicitly list when not to use it or compare to alternatives.

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