Add Surface Element

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the mutation nature is known. The description goes beyond annotations by disclosing that non-applicable style fields are reported in the 'ignored' list, and by explaining connector behaviors (arrows between shapes or points). This adds valuable behavioral context without contradicting annotations.

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 five sentences, each earning its place: purpose, shape variants, connector behavior, usage context, and the 'ignored' field behavior. It is front-loaded with the action and resource, and contains no fluff or redundant content.

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 large schema (30 parameters) with detailed descriptions and an output schema present, the description provides sufficient high-level context: supported element types, connector modes, and response behavior for ignored fields. Full information is available for an agent to select and invoke the tool 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?

The input schema has 100% description coverage, with rich per-parameter details (e.g., fillColor palette family, targetPosition relative/absolute semantics). The description does not add significant parameter-level meaning beyond summarizing element types. Baseline of 3 is appropriate because the schema carries the heavy lifting.

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 the action verb 'Add' and clearly specifies the resource: 'shape, connector, text, or group to the AFFiNE edgeless canvas surface.' It also names the specific shape types and connector modes, and the phrase 'Use for building diagrams programmatically' reinforces the tool's scope. This clearly distinguishes it from sibling tools like update_surface_element and delete_surface_element.

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 a clear context: 'Use for building diagrams programmatically.' It does not explicitly state when not to use this tool (e.g., for modifying existing elements, use update_surface_element), but the sibling relationships and the 'mirrors update_surface_element' note implicitly guide the agent. This is clear context without explicit exclusions.

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