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

Beyond the annotations, the description discloses that each call spawns a NEW widget instead of reusing the existing one, that the connector must already be authenticated, and how often to call it. These are real behavioral traits that no structured field conveys. The new-widget-per-call behavior is a UI presentation effect, not a data mutation, so the readOnlyHint/idempotentHint annotations still hold.

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 front-loaded with purpose, then timing, prerequisites, parameter behavior, and cautions, in that order, and every sentence adds information. The repeated negative guidance (not per tool call, not mid-batch, not twice for unchanged state) closes real failure modes, so it is not padding.

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?

With only two parameters, full schema coverage, and readOnly/idempotent annotations already in place, nothing material is missing. An agent can decide when to call, whether auth is required, what the call produces, and how often to repeat it.

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 already 100%, so the baseline is 3. The description still adds meaning about projectId: passing it jumps straight to that project's preview, while omitting it lets the user choose one of their own projects inside the widget, a nuance that goes beyond the schema's 'omit to use the currently targeted project.'

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 first sentence names a concrete action and artifact: 'Open the embedded ChatCut widget in-document in this chat.' The verb and resource are unambiguous, and the definition goes on to describe exactly what the effect is: a fresh preview lands next to the latest message.

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?

Timing is stated precisely: call it right after a project is first created or targeted, and again after each user-visible change. The exclusion list is explicit too ('not for every tool call, not mid-batch, and not twice for the same unchanged state'), and an authentication prerequisite is called out, so the agent can decide when to invoke it and when not to.

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