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. It signals a read path via 'get', but clear, trash, and restrict are almost certainly destructive and nothing warns about reversibility, required permissions, or side effects on other state.

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?

Two short sentences with no filler, and the read/update distinction plus action list are front-loaded. It is efficient, though arguably too terse to earn full marks.

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?

Fifteen parameters, 27% schema coverage, no annotations, and no output schema leaves the description wholly inadequate: it never maps parameters to actions, which is the single most important thing an agent needs for a multi-action tool.

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. It repeats the action enum that the schema's own 'action' field already documents, and explains no other parameter (id, kind, scope, target, decision, item_action, undo, paths, etc.).

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 verb pair 'read or update' is explicit and the action list narrows the scope, so an agent can tell this touches '/learn state'. But 'magents /learn state' is internal jargon that never says what is actually being read or mutated, and no sibling (e.g. learn_collect) is distinguished.

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 enumerates the six valid actions but gives no condition for choosing among them, no prerequisite, and no mention of how this relates to learn_collect or the other learn/memory siblings. The reader must infer everything about when to call this.

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