list_workspaces

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

No annotations are supplied, so the description carries the full burden. It does disclose meaningful behavior: results are machine-local and newly created or joined workspaces appear immediately without a refresh. However, it says nothing about what each workspace entry contains, ordering, or whether discovery is automatic, and the hardcoded 'No Jotbus workspaces are connected on this machine yet' is a stale-state claim baked into a static definition that may be false at call time.

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 opening sentence is well front-loaded, but the second sentence is a snapshot of current environment state that does not belong in a reusable tool definition and will become wrong. Removing it would leave a tighter, more durable description; as written, roughly half the text is volatile noise.

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 list tool with no output schema, the description covers the essentials: what is listed, its local scope, the empty-state remediation, and immediate visibility of new workspaces. The main gap is that it never indicates the shape or identity fields of a workspace entry, which an agent would want when choosing one to pass to another tool.

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, which is the baseline-4 case, but the description adds no parameter meaning at all. Its only scoping statement ('on this machine') reads more like a result constraint than an input, so the definition contributes nothing the empty schema would not already imply.

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 gives a specific verb and resource: 'List the Jotbus workspaces connected on this machine', and it scopes the result to the local machine, which distinguishes it from anything server-wide. It also names the sibling create_workspace, so the agent can route correctly. The following sentence describes momentary machine state rather than the tool's function, which dilutes if not obscures the purpose.

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 clearly states the remedy path when the list is empty: use create_workspace or have the user run `npx jotbus` / `npx jotbus join <invite>` in a terminal, noting the workspace 'becomes available here right away'. That is actionable when/when-not guidance tied to an alternative tool. What is missing is any explicit statement about when to prefer this over jotbus_help, the other sibling.

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