tv_app

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

With no annotations, the description carries the behavioral burden. It clearly defines the supported app set and discloses the deep-link/profile limitation. It stops short of stating error behavior when an unsupported app name is passed, but for such a simple launcher this is largely sufficient.

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?

Two sentences with no filler: the action and allowed values come first, and the limitation with routing to the sibling comes second. Every sentence earns its place.

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 one-parameter TV app launcher, this is complete: the agent knows what to call, which values are accepted, and what to use instead for deep links/profiles. The absence of an output schema is not a gap here because the tool is a simple side-effecting launch command.

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?

The input schema only says 'App name', while the description provides the actual accepted values: youtube, youtube_music, youtube_kids, netflix, disney, prime, spotify, jellyfin, skyshowtime, and hbo. This is concrete semantic value beyond the 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?

States a clear action (launch) and resource (app on TV), then enumerates specific supported app names. It also distinguishes itself from tv_play by explicitly saying deep links and profiles are out of scope.

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?

Explicitly says to use tv_play when deep links or profiles are involved, which gives the agent a firm routing rule. The supported app list also tells the agent exactly which inputs are valid for this tool.

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