game_console

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

No annotations are provided, so the description must carry the full burden. It does disclose important runtime behavior: the 'via' parameter's auto mode and the Python routing workaround when the game is hosted by the editor binary. However, it does not mention that running arbitrary console commands may mutate game state, have side effects, or require special permissions—significant gaps for a command-execution tool with no annotation hints.

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 front-loads the primary purpose, then provides usage examples, and finally explains the 'via' parameter. It is moderately long but every section adds meaningful context. The structure is logical and scannable, though the third paragraph on 'via' could be tightened without losing content.

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?

The description covers the main usage scenarios, gives concrete command examples, and explains the critical 'via' routing logic. Since an output schema is present, return-value details are not required here. However, it omits the semantics of 'settle' and does not warn about potential state changes from console commands, which an agent would need to safely invoke the tool in all contexts.

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. It thoroughly explains 'via' (auto vs. cmd vs. python) and why 'auto' should be the default, which adds value beyond the bare schema. But it says nothing about 'settle' (a numeric parameter with a default of 0.15) or the expected format of 'command' beyond examples. With one parameter entirely undocumented, the description fails to fully compensate for the zero-coverage 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?

The description opens with a clear verb-resource pair: 'Run a console command and return the log lines it produced.' It distinguishes itself from siblings like game_state or game_log by referencing command execution and log output, and it provides concrete examples ('stat fps', 'getall') that sharpen its purpose as a generic command runner rather than a structured-state reader.

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?

The description gives clear context: it is useful 'beyond cheats' and specifically for reading values 'until a structured state API exists,' implying it is a fallback when game_state is not sufficient. However, it does not explicitly name sibling alternatives (e.g., game_state) or state when not to use it, so the guidance is implied rather than explicit.

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