keyboard

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

No annotations are provided, so the description carries full burden. It details behavioral traits: text is typed character by character, key presses specific named keys, differences for TV targets (only text allowed, focus required), delay behavior (ignored on Vega and TV), and failure conditions (unsupported key, backend unreachable). This is comprehensive for a mutation tool.

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 slightly long but well-structured with clear sections (purpose, usage, return, parameters, target-specific notes). It is front-loaded with the core purpose. Some redundancy exists (e.g., repeating 'not supported on TV' in two places), but overall it communicates efficiently.

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?

Given the tool's complexity (multiple target types, 4 parameters, no output schema), the description covers all necessary aspects: behavior, parameters, target-specific nuances, failure modes, and return value. It is fully self-contained and leaves no major gaps for the agent.

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 100%, but the description adds value beyond the schema. For 'key', it reiterates the unsupported on TV and suggests 'tv-remote'; for 'text', it mentions uppercase and punctuation; for 'delayMs', it explains when ignored. While the schema already defines parameters, the description provides essential context for correct 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 clearly states the tool types text or presses special keys on various devices. It specifies the verb 'type' and 'press', identifies the resource ('keyboard events'), and distinguishes from sibling tools like 'tv-remote' for navigation. The return type and target devices are also mentioned.

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 explicitly states when to use the tool (enter text or trigger named keys) and when not to (prefer remote tools for D-pad on TV). It provides alternatives like 'tv-remote' for focusing text fields on TV targets, and notes that 'key' is not supported on TV, guiding the agent to use 'text' instead.

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