xae_deploy

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

Beyond the destructiveHint annotation it discloses important behavior: the pipeline halts at the first build error, a single confirmation token covers all the destructive steps, and it refuses on XAE/ADS target mismatch. This is meaningful context the annotations alone do not convey, though the effect of a mid-pipeline failure on already-saved/built state is not detailed.

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?

Three tight sentences, each earning its place, with the operation pipeline front-loaded before the failure/confirmation/precondition caveats.

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?

An output schema exists so return values need not be described, and the description does cover the key precondition, failure semantics, and confirmation requirement for a highly destructive composite tool. The gap is the undocumented parameters, which leaves an agent guessing at skip_build and plc_project_path.

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% and all four parameters (skip_build, confirm_token, plc_project_path, allow_target_mismatch) are undocumented in the schema. The description only indirectly gestures at confirm_token ('one confirmation covers all steps') and allow_target_mismatch ('refuses when targets differ'); it never explains skip_build or plc_project_path.

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 names the exact sequence of operations (save, build, boot-project autostart, activate, restart) performed as a single composite action. This clearly distinguishes it from the granular siblings like xae_build, xae_activate_configuration, and xae_restart_twincat, which do only one step.

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?

It signals this is the one-call alternative to the step-by-step siblings and gives a concrete pre-condition for refusing ('when the XAE target and the ADS target of this server differ'). It does not, however, explicitly name the individual tools to use instead or state when a caller should prefer the granular path.

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