learn_state

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

No annotations are provided, so the description carries the full behavioral burden, yet it only says the tool 'reads or updates' state. It does not disclose that actions like clear, trash, and restrict are destructive, whether 'undo' makes changes reversible, or what permissions are needed — a significant gap for a mixed read/write tool.

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 two sentences are front-loaded and waste no words, but for a 15-parameter tool with branching actions this level of brevity is under-specification rather than concision. Nothing earns its place beyond the action enumeration.

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?

With 15 parameters, no annotations, no output schema, and 27% schema coverage, the description leaves the agent without enough information to invoke the tool correctly for any action beyond the trivial 'get'. This is completely inadequate for the tool's 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?

Schema description coverage is only 27% across 15 parameters, so the description must compensate and does not. Ten-plus parameters (kind, mode, note, path, undo, paths, scope, status, target, run_dir, run_name, item_action) are left entirely unexplained, and the one enum it restates (action) is already documented in the schema.

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?

States a specific verb pair ('read or update') and resource ('magents /learn state'), plus enumerates the six valid actions, so the agent knows the tool's domain. However, it does nothing to distinguish it from the sibling learn_collect, which also operates on the /learn surface, so it falls short of a 5.

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 lists the action values but gives no guidance on when to use get vs set vs decide vs trash, and no indication of how this differs from learn_collect or the other sibling tools. The agent must guess which action applies to its situation.

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