send_gcode

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

With no annotations, the description carries the safety burden and does disclose that some dangerous commands are blocked and that delivery can target all printers. However, it does not disclose side effects of arbitrary G-code, reversibility, or execution/error behavior, so the transparency is partial.

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?

Two sentences, zero filler, with the core action and scope front-loaded and the safety caveat in the second sentence. Every phrase contributes.

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?

The schema covers parameters richly and the description establishes the raw/safety context, which is enough for basic invocation. It is missing guidance on when high-level siblings should be preferred and what the tool returns or does on failure, leaving the agent to infer those.

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 100%, so the schema already documents both parameters well, including examples and the blocked list. The tool description adds framing ('raw', 'all printers') but no additional parameter-level meaning beyond what the schema provides, matching the baseline for high coverage.

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 action ('Send a raw G-code command') on a clear resource (a printer, or all printers), and the word 'raw' distinguishes it from the high-level printer-control siblings. It conveys exactly what the tool does without needing to inspect the schema.

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 implies this is the low-level escape hatch for arbitrary G-code, while siblings like pause_print, stop_print, and set_temperature cover high-level operations, but it never states when to prefer those instead. It mentions blocks on dangerous commands but no explicit when-to-use/when-not-to-use guidance.

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