view_control

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

With no annotations, the description carries the full burden; it usefully discloses that the operation is display-only and does not alter the image, which is the key safety fact. It says nothing about whether an active document is required, whether the change persists or is session-local, or how conflicting flags (fit + reset + zoom together) are resolved.

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?

A single front-loaded sentence with the most important disambiguation (view, not image) placed first, then the operation list. Nothing is redundant, though the em-dash enumeration is dense enough that combination semantics get squeezed out.

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?

For a 7-parameter, zero-required, unannotated tool, the description covers what each option does and confirms no image mutation, which is the essential part. The gaps around mutual exclusivity of fit/reset/zoom and the absence of any statement about the result or required document state leave real ambiguity.

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 0%, so the description must compensate, and it largely does: it maps zoom (1.0 = 100%), rotation in degrees, mirror, fit, reset, and centre-on-point to the seven parameters. It omits units/coordinate space for center_x/center_y and gives no precedence rule when multiple parameters are supplied at once.

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?

States a concrete verb (move) and resource (the user's view of the canvas) and immediately scopes it with "not the image", which separates it from siblings like rotate_image, flip, and transform_layer. The enumerated operations (zoom, rotation, mirror, fit, reset, centre) make the tool's surface fully legible.

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 phrase "not the image" plus the example "e.g. to show the user what you changed" give a clear condition for choosing this over image-transform siblings. It stops short of explicit when-not guidance (e.g. don't use this to persist a rotated result — use rotate_image).

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