bpb_get_phase

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

With no annotations present, the description carries the full burden and does add genuine behavioral facts: it is lightweight, callable safely mid-battle, and has no side effects on the backpack. It stops short of explicitly declaring read-only semantics or describing return value shapes beyond the field names.

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 clauses, front-loaded with the returned fields followed by the safety/usage note. Every element carries information; only minor cost is that the field list is a bare enumeration without explanation of individual fields.

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?

There is no output schema, so the description must convey return content, and it does list the fields plus the key usage scenario. It could go further by explaining what values 'state' or 'survival' can take, but for a zero-parameter lightweight getter it is adequately complete.

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?

The tool takes zero parameters, so the baseline is 4. The description's field enumeration describes the response rather than inputs and does not conflict with anything in the empty 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?

The description states the tool returns lightweight state and enumerates exactly which fields (state/round/tries/gold/wins/total_wins/survival/can_skip_result/last_result), which is a concrete resource. It implicitly separates itself from bpb_get_state by calling itself '轻量' and saying it does not touch the backpack, though it never names that sibling explicitly.

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?

It gives clear usage contexts: safe to call during battle, for waiting on resolution, or for deciding whether to advance to the next phase. It does not name alternatives such as bpb_wait_for_result or bpb_get_state, so the routing guidance is contextual rather than explicit.

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