run_command

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

Annotations already flag destructiveHint=true and non-read-only, but the description adds genuinely new behavioral context: backend restriction, blocked command classes, and the env-var gate for LISP. It does not, however, describe failure behavior or how commands are acknowledged, which would complete the picture for a destructive tool.

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 compact sentences with zero filler; the core purpose and the backend constraint are front-loaded before the edge-case env-var note.

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 and annotations carry the safety profile, so the description does not need to explain returns. It covers the backend and permission constraints well; the only gap is not steering the agent toward dedicated tools when they exist.

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% and already gives the format (e.g. '_.FILLET R 5 ') and the newline-as-Enter convention, so the baseline of 3 applies. The description adds no additional meaning about the 'command' parameter beyond what the schema provides.

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 (send) and resource (raw input to the AutoCAD command line), which cleanly separates it from all sibling tools that operate on structured entities or drawings. The '(AutoCAD backend only)' qualifier further narrows scope, so an agent can identify this as the escape-hatch tool without opening 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?

It specifies two hard preconditions (AutoCAD backend only, POWER_CAD_ALLOW_LISP=1 for AutoLISP) and notes that shell/script/loader commands are blocked, which is real routing guidance. However, it never says when to prefer this over the many dedicated siblings (draw_line, create_layer, etc.) or that raw commands should be a fallback.

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