annotation

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

Annotations already include readOnlyHint=false, indicating mutation. The description adds no further behavioral context, such as whether operations modify the current drawing, prerequisites for coordinates, or potential side effects. It is purely a list of operations with data fields, providing no disclosure beyond what the readOnlyHint already implies.

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 a compact, well-organized list. It front-loads the purpose and then enumerates operations with their required data fields in a consistent, scannable format. Every line is informative and there is no redundant or filler text.

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's complexity (six distinct operations) and the sparse schema, the description covers the essential information needed to invoke each operation. An output schema exists, so return values need not be explained. However, it omits contextual details like coordinate system, units, or the effect of include_screenshot, leaving some ambiguity for an agent without prior AutoCAD knowledge.

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 is extremely generic (data is an untyped object), so the description is essential to know which fields each operation expects. It lists the data structure for every operation, enabling an agent to pass correct parameters. However, it does not explain the meaning of coordinate fields (e.g., x, y, dim_x) or units, which would add further semantic value.

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 clearly states the tool's scope: 'Annotation: text, dimensions, and leaders.' It then lists specific creation operations (create_text, create_dimension_linear, etc.), making it obvious this tool creates annotation entities. This distinguishes it from siblings like 'layer' or 'entity' which handle different drawing aspects.

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 list of operations provides clear context that this tool is for creating annotations, and the separation from sibling tools (layer, drawing, etc.) makes the usage context obvious. However, it does not explicitly state when not to use this tool or name alternatives, so it lacks the explicit exclusion guidance that would earn a 5.

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