Drawing Settings (read / change)

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

With annotations only stating readOnlyHint=false and destructiveHint=false, the description carries the burden of disclosing behavioral nuance. It does so by enumerating the exact system variables it wraps and explaining the no-argument return behavior. The explicit distinction between dimension-related parameters and standalone text size is a valuable transparency addition. No contradiction with annotations is present.

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 three sentences, each serving a purpose: stating the operation, explaining the facade and no-arg behavior, and disambiguating dimension vs. text settings. The sysvar list is lengthy but justified for transparency. The structure is front-loaded with the core purpose and avoids fluff, though it is slightly dense.

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?

Given the tool has a rich input schema, an output schema, and annotations, the description is complete for its complexity. It covers read/write behavior, usage patterns, the full set of friendly keys, and a key semantic nuance. No additional behavioral or return-value documentation is needed because the output schema exists and the description adequately addresses the tool's role.

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?

The input schema already covers the single `settings` parameter with 100% description coverage, including keys and an example. The description adds semantic meaning beyond the schema: it maps friendly names to system variables and highlights the subtle difference between text_size and dim_text_height. This contextualization helps the agent choose the correct keys and understand their effects.

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 specific verb+resource construction: 'Read or change common AutoCAD drawing settings by friendly name.' It clearly identifies itself as a convenience facade over system variables (INSUNITS, LUPREC, LTSCALE, etc.), distinguishing it from sibling tools like system_get_variable and system_set_variable. The explicit list of wrapped variables and the example use case further solidify its scope.

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 provides clear usage context: 'Call with no argument to get a full snapshot of the current settings' and explains the friendly-key mapping with an example. It also clarifies the potential confusion between dim_text_height (affects dimensions) and text_size (does not touch dimensions), which helps prevent misuse. It does not explicitly name alternatives like system_set_variable, but the facade framing makes the intended use evident.

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