game_pad

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

With no annotations provided, the description carries the full burden. It clearly discloses input conventions (range -1..1, UE forward = +1), the hold behavior (keeps input after return, cleared by game_reset_input), and the state parameter's effect (returns exact positions instead of a picture). It also implies that without hold, inputs are released after the call. No annotation contradiction exists.

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 front-loaded with the core action and result, followed by organized parameter details and three concrete examples. Every sentence serves a purpose—no fluff. It is substantial but well-structured, making it easy to scan.

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 tool with 14 parameters, no output schema, and no annotations, the description is remarkably complete. It covers input specification, conventions, hold lifecycle, and how to get positional data. The examples give direct call patterns. The few omitted parameters are minor and do not hinder an agent from using the tool correctly.

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%, so the description must compensate for 14 parameters. It thoroughly explains the core ones: buttons (with full list and aliases), sticks (lx/ly, rx/ry, l2/r2), range, hold, state, and demonstrates duration via examples. However, it omits explanations for grid, observe, show_ui, and max_size, which remain ambiguous. This is a minor gap given they are likely less critical for typical usage.

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, specific verb ('Press pad buttons and push sticks') and a resource ('pad'), and explicitly ties it to a duration and observation step. It distinguishes itself from sibling tools like game_pad_sequence (sequence vs single action), game_key/game_mouse (different input types), and game_observe (observation without input) by stating both action and result.

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?

While not explicitly naming alternatives, the description provides multiple examples covering typical scenarios (run forward, jump while running, and requesting exact state) and explains the hold parameter with a clear instruction to clear it via game_reset_input. It implicitly guides when to use this versus other tools, but does not explicitly state 'use this instead of X when...'.

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