annotate_screenshot

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

With no annotations to rely on, the description fully discloses side effects ('copy it to the clipboard', 'show it to the user'), coordinate origin ('origin TOP-LEFT'), and return behavior ('Returns the marked image'). It also warns about the need to actually view the screenshot, preventing common agent missteps.

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 dense but every sentence contributes valuable guidance, from the workflow note to the coordinate example. The example is somewhat lengthy, but it directly addresses a common source of errors and is worth the space.

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 of the tool and no output schema, the description covers all necessary aspects: prerequisite workflow, coordinate system, shape-specific semantics, and return value. It does not mention error handling or edge cases, but those are less critical for this tool.

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 only briefly documents 'output' and 'clipboard'; the description adds critical semantics for 'marks', including point order for each shape type and a concrete coordinate example. This transforms an otherwise opaque parameter array into a usable specification.

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 'Draw on a screenshot you already took, then copy it to the clipboard and show it to the user', specifying the exact verb, resource, and side effects. It distinguishes itself from siblings like 'take_screenshot' by operating on an existing screenshot and producing annotated output.

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?

Explicitly instructs 'Call take_screenshot first', establishing a clear prerequisite workflow. It also details coordinate semantics and shape-specific point order, implying when to use this tool. While it doesn't list alternative tools, the context is clear enough to avoid misuse.

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