Run AutoCAD Command

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

The description discloses critical behavior not visible in annotations: the need to append '\n' for Enter, the extra blank line or '_X\n' to exit option menus, and the deadlock risk if the prompt is left open. It also reveals the verb denylist as a guardrail, not a security boundary, which is an important caveat for the agent.

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?

The description is longer than average but every sentence carries meaningful information: a usage pattern, a deadlock warning, and a guardrail/security clarification. It is structured with the example first and the warning clearly marked 'IMPORTANT'. Slight redundancy in the example could be trimmed but the length is justified by the complexity.

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 description fully covers the single parameter's syntax, the most common failure mode (deadlock), the limitations of the denylist, and exactly which sibling tools to use instead. With the output schema and annotations present, nothing critical is missing for an agent to invoke it correctly.

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 100%, so the baseline is 3. The description adds value by explaining the '\n' convention, giving examples, and describing the extra blank line requirement for commands ending at option menus. This goes beyond the schema's simple 'AutoCAD command string' description.

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 states 'Execute an AutoCAD command string directly (COM backend only)', which clearly identifies the verb (execute), resource (AutoCAD command string), and the technical context (COM backend). It is also differentiated from sibling tools like system_run_lisp by its focus on command strings rather than LISP code.

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 explicitly tells the agent to prefer typed sibling tools (entity_delete, drawing_save_as, block_insert, drawing_purge) and explains why: they validate arguments. It also warns against using this tool for destructive commands, which is clear guidance on when not to use it.

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