Launch / Attach AutoCAD

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds real behavioral context — idempotent-ish attach-vs-launch semantics, the reported fields, and three explicit refusal conditions. That is well beyond the annotation surface, though it omits launch latency/failure handling.

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?

Front-loads the core behavior and refusal list in two dense sentences with no filler. The trailing "Pack: settings · lean: no" is internal jargon that costs a little clarity without adding meaning for an agent.

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, so return values needn't be spelled out (though the description lists them anyway). For a stateful connect-or-launch tool, the description covers the important failure modes; only environment prerequisites (e.g., how CAD_PROGID is set) are left implicit.

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 both `visible` and `open_path` are already documented in the schema. The description only adds that open_path is subject to path validation, which is marginal extra meaning over the schema baseline.

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 (connect to the app named by CAD_PROGID) with the exact dual behavior (attach if running, launch otherwise) and the fields it reports. This distinguishes it cleanly from siblings like drawing_open, system_status, or document_activate.

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?

Gives concrete refusal conditions (headless mode, capability "live_application", failing open_path validation), which effectively tells the agent when the tool will not work. It stops short of explicitly naming the alternative to use in those cases (e.g., what to do in a headless session).

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