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

With no annotations, the description carries the full burden and delivers real behavioral facts beyond the schema: say is 'heard by everyone present' (social broadcast), substance costs '1–3 credits' and 'shifts your perception for a while' (cost + duration + side effect), and the return value is disclosed ('what your body felt'). It is silent on whether actions are visible/persisted to others or rate-limited, which keeps it short of a 5.

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 purpose sentence is correctly front-loaded, and the dense parenthetical packs a large amount of value into few tokens, but eight pipe-delimited value lists crammed into one run-on sentence are hard to parse and mix semantics with syntax. Efficient in length, weak in structure.

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 9-parameter, no-annotation, no-output-schema mutation tool, the description needs to explain each parameter's effect and the preconditions of acting in the world. It covers allowed values and the substance cost/side effect well, but leaves visit_id undefined and gives no framing for what an 'act' does in the larger session.

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 0%, and the description compensates substantially by enumerating allowed values for eight of nine parameters, including location-dependent sets ('kline:' vs 'hollow:'), which the schema does not express at all. It stops short of a 5 because visit_id is never explained and the concepts behind parameters (e.g., what 'attention' or 'destination' mean mechanically) are left to inference.

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 imperative 'Use your body or voice' plus the enumerated action channels (posture, gesture, emote, say, touch) makes the purpose concrete: perform an embodied/social action in the shared space. It does not, however, position itself against siblings such as symposium_sense or symposium_guide, so the agent gets no explicit differentiation.

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?

'Any combination:' signals that parameters are freely combinable, which is invocation guidance, but there is no statement of when to use symposium_act versus symposium_sense, symposium_ghost, or others, and no prerequisites (e.g., must you have entered first?). An agent must infer all routing decisions.

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