bpb_start_run

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

With no annotations, the description carries the full burden and does well: it discloses that force_new deletes the suspended run (a destructive side effect), that HP max is forcibly reset to 25 rather than inherited, and that hp is returned. It does not cover error behavior or whether ranked runs have side effects like rating changes.

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?

Front-loads the core action, then defaults, then the force_new override, then side effects, then optional parameters. Dense but every clause carries information; the parenthetical about corrupted saves is the only mildly expendable phrase, and even that aids tool selection.

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?

For a 4-parameter state-mutating entry point with no annotations and no output schema, the description covers defaults, the destructive override, the HP-reset side effect, and the partial return value (hp). What remains thin is the interaction with bpb_set_class/bpb_set_loadout for the optional parameters and any error conditions.

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 25% (only force_new is documented in the schema), so the description must compensate, and it does: mode values are restated with their meaning, force_new's destructive semantics are spelled out, and class_id/loadout are explained as pre-game class and starting loadout selection. The numeric ranges (0-6, 0-2) and the consequence of an invalid or omitted class_id are left to 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 and resource ("开始新的一局" / start a new run) and immediately clarifies the default resume-suspended-run behavior, which separates it from a plain fresh start. It does not name the sibling tool bpb_continue explicitly, so the differentiation from siblings is implied rather than explicit.

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?

Gives a clear default (resume suspended run) plus the precise condition for the alternative (force_new=true for corrupted old saves or a crashing continue). It lacks an explicit "use bpb_continue instead when X" routing statement, but the when-to-use-which signal is strong and actionable.

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