annotation

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

Annotations include readOnlyHint: false, indicating this is a write operation. The description lists create operations but does not disclose additional behavioral traits such as coordinate system expectations, layer requirements, or impact on existing drawing state. Beyond the raw operation names, little is added to what the annotation already signals.

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 concise and well-structured: a one-line overview followed by a bulleted list of operations with their data schemas. No unnecessary prose or repetition. It front-loads the main purpose and uses a scannable format, though it could benefit from brief explanations of each operation.

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 (6 distinct operations) and the sparse schema, the description provides a functional reference but lacks deeper context. It does not explain concepts like 'leader', units for coordinates, or how screenshots factor in. An output schema exists, so return values are not needed, but overall completeness is only adequate.

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 minimal (data, operation, include_screenshot) with 0% description coverage. The description compensates by enumerating the valid operation values and providing a data structure for each operation. This adds critical meaning that the schema lacks, though some fields (e.g., dim_x, offset) remain underspecified.

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 identifies the tool as handling annotations: text, dimensions, and leaders. It lists six specific create operations, making the purpose distinct from sibling tools like 'layer' or 'entity'. However, it does not explicitly state that this is for creating annotation objects in a drawing, but the operation names make it unambiguous.

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?

No explicit guidance is given on when to use this tool versus alternatives. The operation names imply usage (e.g., 'create_text' for text annotations), but there is no context about prerequisites, selection criteria, or exclusions. An agent would have to infer when to choose 'annotation' over 'entity' or 'drawing'.

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