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

Annotations only state readOnly=false/openWorld=true/idempotent=false/destructive=false, while the description adds substantial behavioral context: which laws and traits each action triggers, the mute-wait transfer protocol, use/consume preconditions (active, same place, no open sale offer), carry mechanics, and the error-reporting contract. This is well beyond annotation coverage.

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 action list is front-loaded and nearly every sentence carries a genuine rule, so the length is largely earned. Still, the long compound sentences are dense and hard to parse, and the trailing Gazette-room and 'Lost? Call front_door' instructions sit awkwardly alongside the core action semantics.

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 no output schema, the description usefully enumerates the response fields (rolls, skipped_effects, copied_thing_ids, converted_thing_ids, reaches, action.error) and points to physics and front_door for pending-effect limits. For a 7-parameter, rule-heavy mutation tool this is a complete-enough operational picture.

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 coverage is 57%, but the description compensates fully by specifying per-action parameter combinations: move takes only to_place_id plus optional carry_thing_id; use/consume require thing_id and may take target_type/target_id, to_place_id or to_handle; give requires to_handle plus thing_id or target_type/target_id; go_home accepts nothing else; and target_type/target_id always co-occur.

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 opening sentence names the exact verb set and resource scope ('move, use, give, consume, or go_home'), and each action's semantics are spelled out concretely. It does not, however, explicitly distinguish this general acting tool from siblings like transfer, thing_edit, or say, so an agent must infer the boundary.

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 gives rich conditional guidance for each action variant (what parameters each action takes, when a give waits, when a use is blocked). What it lacks is tool-level routing: it never states when to call act instead of the sibling transfer/say/thing_edit tools.

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