annotate_infer

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

With no annotations provided, the description carries the transparency burden. It discloses a key behavior: '不修改原图' (does not modify the original image), and clarifies how modes work. However, it does not describe the output/return format or any other side effects, which is a gap given there is no output schema.

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 extremely concise, consisting of two sentences that convey the core purpose, modes, and key safety behavior. Every phrase adds relevant information without redundancy.

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 complexity (8 parameters, no output schema, no annotations), the description provides a solid overview, covers modes, clarifies non-destructive behavior, and gives examples for items and question. However, it omits explicit return-value semantics, which would improve completeness, but is largely adequate due to strong schema coverage.

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 schema already has 88% coverage, providing baseline. The description adds value by explaining the modes (virtual vs overlay) and listing annotation types (框/点/连线/箭头/圆) that map to the items parameter, beyond what the schema states. It also gives an example of the question parameter.

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 purpose: '虚拟标注 + 增强图形推理' (virtual annotation + enhanced graphical reasoning), with specific actions like injecting annotations into the vision model to guide spatial reasoning. It distinguishes itself from sibling tools like annotate_image by adding the reasoning component, and details two modes (virtual and overlay).

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 implies usage for spatial relationship reasoning and explains mode selection (virtual vs overlay), but it does not explicitly state when to use this tool over alternatives or mention exclusions. No comparison with siblings like annotate_image or describe_image is provided.

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