open_workbench

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

With no annotations provided, the description carries the full burden, and it does disclose a genuine behavioral trait: host capability determines whether a UI is rendered. It does not state whether the call is read-only, whether it mutates session/selection state, or what the caller receives back, so the behavioral picture is only half-drawn.

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 short sentences, front-loaded with the action, and the host-capability caveat follows. The clause "an embedded UI is never required for the workflow" largely restates the preceding sentence's point about non-MCP clients, so there is a small amount of redundancy.

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 zero-parameter tool with no output schema and no annotations, the description covers the host-compatibility question well. It is still incomplete on the essentials an agent needs: what the workbench surfaces after opening, whether any state changes, and how it relates to workbench_action in the same family.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline is 4. Schema coverage is 100% and no parameter semantics are needed.

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?

It states a verb and resource ("Show the unified ... workbench") and enumerates the surfaces it unifies (task, selection, preview, generation, review), so the intent is not a pure tautology. But it never says what calling it actually accomplishes for the agent, and it draws no line against the sibling tool workbench_action, which an agent must distinguish 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?

It gives real conditional guidance: MCP Apps-capable hosts can render it in chat, other clients can use the normal tools, and an embedded UI is never required. That tells the agent when this tool is appropriate and when it can be skipped. It stops short of naming alternatives explicitly (workbench_action, resume_workflow) or stating any prerequisite.

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