Pan and zoom the view

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

Annotations indicate readOnlyHint=false and idempotentHint=true, meaning the operation can have side effects but repeated calls are safe. The description adds critical behavioral information: it requires the canvas to be drawn in the GM's browser (a precondition not inferable from annotations), and it states that the sceneIdentifier acts as an optional safety check (nothing happens if the GM is on the wrong scene). It also notes that forEveryone pulls all players, which is a side effect worth disclosing. It doesn't detail reversible nature, but the idempotent hint covers that.

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 two sentences, the first clearly states the main action, and the second handles the special condition. It is efficient and front-loaded, with no fluff. Minor point: it could be slightly more structured, but the brevity is appropriate for the tool's 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?

Given the tool has 7 parameters with 100% schema coverage and no output schema, the description sufficiently covers the core purpose, prerequisites (canvas overhead, write permissions), and safety checks. It does not mention edge cases like invalid coordinates or scale bounds, but the schema covers format. The description is complete enough for an agent to invoke correctly, especially with the sceneIdentifier guard.

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 100%, so the schema already documents all 7 parameters with clear meanings (e.g., x/y center coordinates, scale zoom, tokenId id or name, duration range). The description adds value by clarifying the overall behavior of parameters: that x/y and tokenId are mutually exclusive (implied by the two methods), and that sceneIdentifier is a 'check' that triggers no action if mismatched. It also implies that duration is optional with a default, which is in schema but the description reinforces this. The 'forEveryone' purpose is clarified in the description, which is a small addition.

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 action ('Move the Gamemaster's view') and the resource (camera/view), with two distinct use cases: positioning to a token or point and setting zoom, including an optional group 'pull' behavior. This is specific and distinguishes it from sibling tools like 'get-canvas-view', 'ping-canvas', or 'move-token' by focusing on the GM's view manipulation rather than token placement or querying.

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 indicates when to use it: when the GM needs to move the view or zoom, and when forEveryone is used to sync all players, with a prerequisite of 'Allow Write Operations'. It does not explicitly mention alternatives like 'ping-canvas' for lightweight alerts, but the context is clear enough that an agent would know to use this for camera movement rather than other view-related tools.

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