bg3_se_eval

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

With no annotations, the description carries the full burden and does flag the critical trait: 'This executes code in the user's live game session', warning of real side effects. It also explains the delay's behavioral intent. It omits error/failure behavior and whether state persists, which matters for arbitrary live code.

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?

Tight and front-loaded: the core action leads, then per-parameter notes, then a closing safety caveat. Every clause carries information; only the bare 'context:'/'delay:' fragments make it feel slightly terse rather than polished.

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?

An output schema exists, so return-value explanation is fairly covered. But this is an arbitrary-code-execution tool with zero annotations and no output-side safety framing; missing timeout semantics and failure modes leave the agent under-informed for a high-risk live-session operation.

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 0%, so the description must compensate and largely does: it defines the two contexts with parenthetical api hints, explains delay with a concrete rationale, and names the BG3T harness global. Only 'timeout' goes unexplained, which is the one clear gap against a 4-param 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?

States a specific verb and resource: run Lua inside the running game via Script Extender, and returns printed output plus return value. An agent can tell this is a live-code-execution tool. However, it does not distinguish itself from near siblings like bg3_se_command or bg3_test_script, leaving the agent to infer the boundary.

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 useful in-tool guidance (choose 'server' for game logic, 'client' for UI/visuals; set delay to let a cast or boost resolve) but never says when to reach for this tool versus bg3_se_command, bg3_se_live_entry, or bg3_test_script. Usage is implied rather than routed.

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