Characters meet (experimental)

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

With no annotations supplied, the description carries the full burden and does substantial work: it discloses the per-round loop, the internal think-then-act/speak/stay-silent behavior of each character, and precisely what is returned (director's protocol, first speaker, that speaker's packet). Gaps remain on cost/latency for a multi-round, multi-character LLM orchestration, on what happens at max_rounds, and on whether state persists between calls.

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-loaded with the experimental flag and the core action, then mechanics, then return shape and next step — a sensible order with no filler sentences. The middle sentence describing each character's internal turn is dense but earns its place by explaining observable behavior.

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 complex multi-round orchestration tool with no annotations and no output schema, the description covers purpose, per-round mechanics, and return contents well enough to call it correctly and to know the next call. It stops short of covering failure modes (unknown character ids), termination behavior, or the cost profile of many characters times many rounds.

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 100%, so all five parameters are already documented in the schema, including ordering ('in the order they enter') and the max_rounds cap. The description adds only the 'as strangers' relationship framing and the existence of a 'protocol' that tasks must follow; it does not explain the tasks/events parameters beyond pointing at the protocol. Baseline 3 is appropriate.

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 ('Puts 2-5 saved characters into one situation ... starts a scene') and names the exact sibling that continues the workflow ('record each turn with character_meet_turn'). An agent can distinguish it from character_meet_turn and character_meet_event without opening any schema.

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?

Clear context for use: initiating a scene with 2-5 saved characters as strangers, followed by an explicit hand-off to character_meet_turn for subsequent turns. It lacks explicit exclusions or prerequisites (e.g. that character ids must already exist via character_create/character_save, or when to prefer character_scene instead).

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