Run Self Distill

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

Annotations include destructiveHint=true, which the description aligns with by stating it persists lessons (modifies state). The description adds that it reads conversation logs and detects signals, but does not elaborate on the full behavioral impact (e.g., whether logs are altered or deleted). It does not contradict annotations.

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 consists of two concise sentences. The first sentence delivers the core action and value proposition, and the second adds essential details. Every sentence earns its place with no redundancy or extraneous content.

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 parameters are well-covered by the schema, but the description lacks information about the tool's output/return value. Since there is no output schema, the agent may need to know what the tool returns (e.g., lessons created, status). This gap reduces completeness for a tool that persists data.

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 description coverage is 100%, and the input schema already provides clear descriptions for all three parameters (dryRun, limit, model). The description adds no additional meaning beyond what the schema conveys, so a baseline score of 3 is appropriate.

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 verb (run) and resource (self-distillation agent) and specifies the purpose: auto-evaluate recent agent sessions and generate improvement lessons without human feedback. It distinguishes from sibling tools like infer_lesson_from_history or run_managed_lesson_agent by emphasizing automation and persistence of lessons.

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 implies usage for automated evaluation without human feedback but does not explicitly state when to use this tool versus alternatives (e.g., infer_lesson_from_history, run_managed_lesson_agent). No when-not-to-use or exclusion criteria are provided, leaving the agent to infer context.

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