akai_learn

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

With no annotations provided, the description must disclose behavioral traits. It only states the purpose without mentioning side effects, permissions, or whether the tool is read-only or mutates any state. This is insufficient transparency.

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 very concise (one sentence with a parenthetical) and front-loaded with the tool name and key purpose. However, it is slightly too short to be fully informative.

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 the complexity of a tool involving feedback and threshold tuning, the description lacks context on how the tool behaves, what 'artifact-level' means, and how the parameters (args, stdin) affect the operation. Without output schema, return values are unexplainable, but more detail on the process is needed.

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 input schema covers both parameters with descriptions, so the schema itself provides 100% coverage. The description adds no extra semantics to the parameters, but the baseline of 3 is appropriate since the schema is complete.

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 specifies 'artifact-level feedback and threshold tuning' and categorizes the tool under 'inference', which gives a clear domain. However, it lacks a specific verb (e.g., 'tune thresholds') and does not differentiate from siblings like akai_capability or akai_tier.

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 tool versus other tools like akai_tier or akai_control. The description does not mention alternatives or prerequisites, leaving the agent to infer usage from the vague context.

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