act

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

Annotations already declare destructive=true and idempotent=true, but the description adds substantive context beyond them: identical IDs query while changed content rejects, close-each-prompt handling for AWAITING_INPUT, pause/query behavior for service UNKNOWN, and a strict host approval-timeout retry rule. It discloses real operational constraints, though several clauses are cryptically worded.

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?

After a serviceable first sentence, the description collapses into a single dense run-on covering parameter shapes, error states, and maintenance policy with no headings or sentence breaks to front-load the essentials. Every clause carries content, but the wall-of-text structure makes the critical routing and parameter information hard to locate.

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?

An output schema exists, so return values need not be explained, and the description does cover error states and many action parameter shapes. It is still incomplete for a 34-value action enum with 0% schema coverage: several actions and the top-level identity fields (action_id uniqueness expectations, experience_refs, view) are not fully specified.

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 0%, so the description carries the burden and largely succeeds by enumerating per-action parameter shapes (select={region,positions}, reorder={region,order}, blind={blind_slot}, buy/sell/use/take={region,position}, select_setup_option={kind,position}, and the positions-v1 form for play/discard). It leaves the top-level observation_id, action_id, and experience_refs semantics only partially implied.

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 gives a specific verb and resource: 'Submit one native action bound to current observation_id, unique action_id...'. An agent understands this dispatches a game action, which is distinguishable from siblings like observe and action_status, though the term 'native action' is jargon that is never defined.

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?

Usage guidance is embedded but scattered: 'Choose current visible unlocked candidates; native settings only. Random non-challenge' and the AWAITING_INPUT/Service UNKNOWN recovery flows. However, it never explicitly states when to call act versus action_status, observe, or wait_until_ready, so the agent must infer the routing.

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