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

With no annotations provided, the description carries the full burden and adds substantial behavioral detail: it states the connection precondition, warns that Warden calls may take 5–9 seconds and fail closed at 18 seconds (requiring at least 20 seconds per call), and enforces rules like 'Never simulate,' 'No subagent,' and 'Always seal, including failure.' These are concrete operational traits beyond the schema. It does not define key terms like 'mutation' or 'seal,' but the disclosure is unusually rich for a tool with no annotations.

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 description is dense and front-loads the essential action and required parameters before moving into mode semantics and behavioral directives. Every sentence appears intentional, though the later terse rules ('Never simulate. No subagent. Always seal...') could be structured more clearly. It avoids fluff and repetition.

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 high-complexity tool with 11 parameters, no annotations, and no output schema, the description is only partially complete. It covers critical behavioral rules and the most important parameters, but leaves seven parameters undocumented and does not clarify the tool's precise effect relative to siblings. It is adequate to attempt a basic call but insufficient for full confident use.

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 27% (3 of 11 parameters), so the description must compensate, but it only explains a few parameters: product (lowercase slug or unknown), host (required), mode (adventure/tutorial/training/benchmark with brief semantics), and opponent (classic vs. warden, default behavior). Seven parameters—seed, origin, learn_from, model_claim, host_version, product_plan, and provider_claim—are not addressed at all, leaving significant gaps for an 11-parameter tool.

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 names a specific verb ('Enter') and a specific target ('ScoreIA Room II (Open Labyrinth)'), but it does not explain what 'entering' actually does—whether it creates a session, joins an existing one, or initializes state. Sibling tools like labyrinth_action and observe_labyrinth are not referenced to distinguish this tool's role, so the agent must infer its precise purpose from context.

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 provides some usage context, e.g. 'If you can call this tool, you are already connected' and mode-specific guidance for adventure, tutorial, training, and benchmark. It also says to choose opponent explicitly for adventure and to 'Always seal, including failure,' which implies a follow-up action. However, there is no explicit comparison to sibling tools (e.g., when to use this vs. labyrinth_action) and no clear when-not-to-use guidance.

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