ams_load

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

With no annotations, the description carries the full burden and does so: side effects are disclosed (nozzle heats, currently loaded filament is returned to its slot, new filament purged), the dry-run behavior of the first call is described, and the firmware/permission constraints are named. An agent knows exactly what physical change will occur and when nothing will be sent.

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?

Content is front-loaded: purpose first, then parameter meaning, then preconditions, then the confirm protocol. Dense and mostly economical, though the Bambu Studio analogy and the final firmware paragraph could be tightened without losing information.

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?

No output schema exists, yet the description tells the agent what the first (dry-run) response contains — what would happen plus a confirm code — which is exactly the return-value detail needed for the two-step flow. For a two-parameter hardware mutation tool, prerequisites, effects, and the safety protocol are all covered.

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, and it largely does: 'slot' is defined via a concrete mapping (AMS 1 = slots 1-4, AMS 2 = 5-8) referencing printer_status, and 'confirm' is explained functionally through the two-call flow including that the first response returns the code. It never states the confirm value is an opaque string taken verbatim from the response, which is a small remaining gap.

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 specific verb and resource (load filament from an AMS slot into the nozzle) and grounds it in a familiar reference (Bambu Studio's Load button), making the operation's scope unambiguous. It is clearly distinguishable from the ams_unload sibling, and the description of the internal sequence (unload current filament back to slot, feed new one, purge) removes any doubt about what 'load' entails.

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 states the precondition 'Only when the printer is not printing' and a hard environmental gate: firmware only accepts it in LAN-only mode with Developer Mode, otherwise fall back to the printer screen, Bambu Handy, or Bambu Studio. The two-call confirmation protocol is spelled out with the trigger condition for the second call (only after the user agrees).

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