Zoom

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds no behavioral detail beyond purpose: it doesn't say whether it returns a new cropped frame, whether the original frame is left unchanged, how the crop is applied around an element, or what the output looks like. With no output schema, these gaps matter.

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 single, front-loaded sentence: 'Crop a region from an existing frame or around an element target.' Every word earns its place, there is no repetition of the tool name or title, and the primary operation is stated first. It is appropriately sized for a tool of this complexity.

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?

The tool has 3 parameters, no output schema, and only 33% schema description coverage, so the description must carry more weight. It omits critical invocation details: the meaning of the region array, whether region and target can be combined, whether frame_id is required for region-based cropping, and what a successful crop returns. An agent could call this with incomplete or wrong parameters based solely on the description.

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?

Schema description coverage is only 33%, so the description needs to compensate. It does help by indicating that 'region' and 'element target' are two alternative ways to specify the crop. However, it doesn't explain the coordinate variant of target, the meaning of the 4-integer region array, or how frame_id relates to the operation; those semantics are left to the bare schema, which lacks descriptions for region and the target union itself.

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 states a specific operation ('Crop a region') and the resources it acts on ('an existing frame' or 'an element target'). It clearly distinguishes the two input modes, and among the siblings no other tool performs cropping. However, it doesn't explicitly differentiate itself from tools like screenshot or get_app_state, and the name 'zoom' versus the verb 'crop' introduces a slight ambiguity.

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 implicitly tells the agent when to use the tool: whenever a region of a frame or an element-centered crop is needed. It gives no explicit guidance about when not to use it, no alternatives to prefer, and doesn't clarify whether region and target are mutually exclusive. This is enough to infer basic usage but lacks decisive routing information.

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