print_label_text

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

With no annotations, the description carries the full burden and does substantial work: it discloses the physical device, that dry_run produces only a PNG, the supported tape widths and which are actually verified, the media materials, and that omitting font_size auto-fits to tape height. It omits copies behavior, return values/paths, and failure modes.

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?

Dense line-per-topic layout with the safety-relevant dry_run instruction placed high, and no filler sentences. It is long, but on a 13-parameter tool nearly every line adds distinct information; the segments example is justified by the undocumented nested shape.

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 13-parameter, no-annotation, no-output-schema tool the description covers the overwhelming majority of what an agent needs to call it correctly, including hardware constraints and mode interactions. Remaining gaps are copies and what dry_run actually returns.

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 does: 12 of 13 parameters get concrete meaning, including the tape_mm allowed set, image_position's four modes spelled out with ordering semantics and the text_after dependency, icon_scale's 0.2–1 range, and an inline JSON example for segments. Only copies is left unexplained.

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 opens with a concrete verb+resource: print text (and an image, if provided) as a label on a PT-P300BT. The text-first, image-optional framing implicitly separates it from the sibling print_label_image, but neither sibling is named, so an agent must infer the boundary.

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?

Strong guidance for the riskiest path: 'dry_run=true なら印刷せず… (最初は必ずこれで見る)' explicitly tells the agent to preview first. It also gives selection rules for tape_mm (only 3.5–12 works on this device, only 12 is hardware-verified) and media types. It never states when to prefer print_label_image or printer_status instead.

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