Launch App

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

With no annotations provided, the description carries the full disclosure burden and does so substantively: it reveals case-insensitive matching, the precise error contract (APP_NOT_FOUND plus an `available` list), and the return behavior (the consolidated state after the command). This is meaningful behavioral context far beyond a bare "launches an app." It does not address idempotency — what happens if the target app is already running — which would push it to a 5.

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?

Four short sentences, each earning its place: purpose, input sourcing, error behavior, and return value. The purpose is front-loaded in the first sentence, and every sentence adds information absent from the schema. This is high-density prose with zero waste.

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 single-parameter tool with an output schema present, the description covers what the tool does, where the parameter comes from, what failures look like, and what is returned. The only notable gap is clarity around side effects (e.g., whether launching changes the active input, relevant given the set_input sibling) and behavior when the app is already active. These are minor against the tool's low complexity.

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 lone `name` string parameter carries no documentation in the schema. The description fully compensates: the value must be an exact title from list_apps, matching is case-insensitive, and invalid values produce a known error with a recovery list. Nothing is left ambiguous about how to populate this parameter.

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 opening sentence, "Lance une application par son titre exact," names a specific verb (launch) and resource (application by exact title). This clearly separates launch_app from all siblings — set_power, set_input, list_apps, get_tv_state, etc. — none of which perform app launching. The tool name and description are coherent, giving an agent an unambiguous mental model.

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 establishes the key prerequisite: "Le titre doit être celui retourné par list_apps," telling the agent exactly where to obtain a valid value. It also prepares the agent for invalid input by specifying the APP_NOT_FOUND error and the `available` list it returns, enabling an implicit retry workflow. It stops short of a 5 because it never explicitly contrasts this tool with alternatives such as set_input for changing the active source.

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