kage_learn

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

The description discloses important behaviors: rejection condition when paths are missing, and the ability to override with allow_missing_paths. It also mentions default estimation for discovery_tokens. No annotations exist, so the description covers some behavioral aspects but lacks details on authorization or side effects.

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 concise with 4 sentences, each adding value: purpose, preference guidance, rejection condition, and token cost detail. It is front-loaded with the main action. However, it could be slightly more structured for readability.

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 tool's complexity (12 parameters, no annotations, no output schema), the description is incomplete. It does not explain return values, how the learning interacts with repo memory, or the meaning of most parameters. Critical information for using the tool effectively is missing.

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 only 8%, with only 'discovery_tokens' having a schema description. The tool description adds context for 'allow_missing_paths' and 'discovery_tokens', but does not explain the meaning or expected format of other parameters like 'learning', 'title', 'type', 'evidence', etc. This is insufficient for an agent to correctly populate all parameters.

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 purpose: 'Capture an actual reusable learning from the current session as repo-local memory.' It uses a specific verb ('capture') and resource ('learning'), and hints at differentiation from siblings by mentioning 'Prefer this over diff proposal.'

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?

Some usage guidance is provided: 'Prefer this over diff proposal when the agent knows what was learned.' However, it does not explicitly state when not to use this tool compared to other siblings like kage_context or kage_decisions. The guidance is a single hint without exclusion conditions.

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