propose_lesson

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

Annotations already declare non-read-only, idempotent, and non-destructive. The description adds that the lesson is 'inactive,' implying a state where it won't be active until approved, which is useful. However, it does not explain what happens to the underlying reviewed decisions or any approval workflow. With annotations carrying the safety profile, a moderate score is appropriate.

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 a single, front-loaded sentence that states the action, object, and source with no wasted words. It is appropriately sized for the purpose it conveys.

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?

Despite having an output schema, the tool is complex with 14 parameters and 8 required fields, yet the description gives no context on the proposal workflow, how to construct the required fields, or what 'inactive' means in the lesson lifecycle. The description is too minimal to be fully usable for a tool of this complexity.

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?

The description provides no parameter-level semantics. Schema coverage is 64%, leaving parameters like tags, database_name, freshness_days, idempotency_key, and supersedes_lesson_id without descriptions in either schema or tool description. Key fields like action and trigger are only described as 'Redacted' in the schema, which adds little meaning. The description fails to compensate for these gaps.

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 uses a specific verb 'Propose' with a clear resource 'inactive lesson' and source 'reviewed decisions,' distinguishing it from siblings like record_decision and recall_lessons. The term 'inactive' adds specificity, indicating the lesson is created in a non-active state. This is a clear, non-tautological statement of purpose.

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 explicit guidance on when to use this tool versus alternatives. The phrase 'from reviewed decisions' implies a prerequisite (reviewed decisions exist) but does not state when to prefer this over list_learning_candidates or record_decision. No exclusions or alternative tool names are mentioned.

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