eject_plate

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

Beyond the destructiveHint annotation, it discloses rich behavior: it destroys/sweeps parts, waits for bed cooldown, only runs when idle/finished, aborts on a new print, and rehearses at +25mm with nothing touched. These are exactly the safety-critical traits an agent needs before a destructive call.

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?

Purpose is front-loaded, then the safe workflow, then preconditions, then the fallback. Five dense sentences with no filler; each one carries operational information an agent must act on.

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 destructive, 9-parameter tool with no output schema and only a destructiveHint annotation, the description covers mechanism, sequencing, preconditions, timing (cooldown), and the manual verification fallback. Nothing needed to call it safely is missing.

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 high (89%), so the schema documents most params. The description still adds value by explaining the relationship and staging between dry_run, rehearsal, and confirm, and by tying cool_down to the cooldown behavior, going a step past the schema's field-level text.

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 gives a concrete verb+resource+mechanism: sweep finished parts off the plate with the toolhead, then verify with the camera, plus how the motion physically works (bed in Y, toolhead low). This is clearly distinguishable from siblings like confirm_plate_cleared and configure_eject.

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 lays out an explicit staged workflow (dry_run to inspect G-code, rehearsal to run 25mm higher, confirm for the real sweep), states preconditions (printer idle/finished, waits for cooldown, aborts if a print starts), and names the follow-up tool (confirm_plate_cleared) with the condition that triggers it.

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