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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds non-obvious context: the call performs no side effects and opens nothing, it returns procedural steps with screens/buttons/fields, and the downstream action must be performed through cotlet_browser_*. The dated API-absence note is a useful, if oddly specific, justification. It does not describe response length or formatting beyond "step by step."

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?

Everything is packed into one long, clause-heavy sentence with embedded parentheticals ("screens, buttons, fields", "checked 11 Oct 2026"). The key fact — that this returns instructions rather than data — is buried mid-sentence instead of front-loaded. Trimming the dated API aside and leading with the actual behavior would help.

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 no parameters and no output schema, the description carries the burden of describing the return value, and it does ("how to do it in Bark step by step") plus the follow-up workflow. The main residual gap is the shape/format of that guidance output and whether the response is static or account-specific.

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?

Zero parameters, so the baseline of 4 applies. The description correctly signals that no input is required and that account targeting is implicit ("the user's own Bark account").

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 names the resource (responses in the user's own Bark account) but the stated behavior is a guide-returning tool, not a listing tool: "Returns how to do it in Bark step by step... and opens nothing by itself." The name/title ("List my responses") and the actual behavior (emit instructions) pull in different directions, so an agent must read carefully to know it is not fetching data. It is distinguishable from siblings once read, but the verb is muddled.

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?

Explicitly routes the agent forward: after getting the steps, execute them "with the cotlet_browser_* tools in the user's Bark Cloud Browser," naming the concrete alternative path. It also explains why no direct API route exists ("Bark has no public API for professionals"), which pre-empts the obvious alternative. No explicit when-not conditions are given, but the workflow context is clear.

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