canvas_focus

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

With no annotations, the description does disclose the key non-obvious behavior: this moves the human's viewport (a shared-state side effect) and that highlight triggers a pulsing animation. It does not say whether the call is blocking, what happens with invalid ids, or whether anything is returned.

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?

Two compact sentences with the core action and default-up front and the intent hint last. No filler; every clause carries information.

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 three-optional-parameter viewport tool with no output schema and no annotations, the essential calling information is present. Gaps remain around error behavior with unknown ids and whether the operation completes synchronously, which matter for an agent sequencing calls.

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 coverage is 100%, so the baseline is 3; the description earns above baseline by documenting the default when `ids` is omitted (whole scene) and clarifying that `highlight` causes a pulse. It adds no format detail for `zoom` beyond the schema's example, which is acceptable since the schema covers it.

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?

Specific verb pair (scroll/zoom) applied to a named resource (the human's view of elements), with the default scope stated in parentheses. It is clearly distinguished from read/draw/export siblings by being a viewport-control action, though it doesn't name a sibling to route away from.

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?

"Use it to point while explaining" gives one positive usage context, which is genuinely helpful for an agent narrating to a human. There is no guidance on when not to use it versus canvas_open or canvas_screenshot, nor on sequencing with other canvas calls.

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