Run Managed Lesson Agent

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

Annotations already indicate destructiveHint: true, meaning the tool modifies state. The description adds that it uses LLM or heuristics, providing insights into the tool's behavior beyond the annotation. However, it does not detail exactly what is modified (e.g., writes lessons/rules to a database), though the dryRun parameter implies persistence.

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 highly concise at two sentences, with each sentence providing essential information about the tool's function and fallback behavior. No unnecessary words or 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 core functionality and prerequisite but lacks details on return values (no output schema) and does not explain what 'lesson inference and rule generation' entails. Given the tool's complexity and the absence of output schema, additional context would be beneficial.

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 all parameters described in the input schema. The description does not add additional meaning or context for the parameters (dryRun, limit, model) beyond what the schema already provides, so it meets the baseline but does not exceed it.

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 runs an LLM-powered lesson inference and rule generation agent over accumulated feedback, using a specific verb and resource. It distinguishes itself from sibling tools like 'capture_feedback' or 'retrieve_lessons' by focusing on agent execution rather than raw data capture or retrieval.

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 mentions the prerequisite (ANTHROPIC_API_KEY for LLM mode) and the fallback behavior, providing clear context for when the tool can be used. However, it does not explicitly state when to prefer this tool over alternatives like 'infer_lesson_from_history' or 'reflect_on_feedback', leaving some ambiguity.

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