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

Annotations declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description is fully consistent, adding the concrete behavioral fact that nothing is opened or mutated and that the return payload is step-by-step navigation instructions. The added note about Phorest API credentials coming only via Support is useful context for why the browser route exists. It does not describe response size, failure modes, or what happens if the user is not logged into Phorest.

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 operative information (returns steps, does not act, then use cotlet_browser_*) is front-loaded and clear. But the opening 'from ChatGPT, Claude or any AI agent' is marketing filler and the API paragraph is long, defensive, and anchored to a dated check ('checked 8 Nov 2026') that adds noise rather than decision value.

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 zero parameters, no output schema, and read-only annotations, the description covers what an agent needs: what is returned (screens, buttons, fields), that nothing is executed, and which tools execute it. The remaining gap is the unaddressed mechanics of where the client identity and note text enter the flow, given the tool has no inputs.

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 with a 100%-covered (empty) schema, so per the baseline there is nothing for the description to explain. That said, a tool named 'add client note' with no client identifier or note-text input is unexplained, and the description does not clarify that the caller supplies those details to the downstream browser tools instead.

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 makes clear that this tool does not perform the write itself: it 'Returns how to do it in Phorest step by step (screens, buttons, fields) and opens nothing by itself', then points to the cotlet_browser_* tools that actually perform the action. The verb+resource is specific (add a client note in Phorest) and the surprising guidance-only nature is stated. It falls short of 5 because an agent skimming by name could still assume this mutates data, and the name/title carry that misleading framing.

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 the follow-on workflow explicitly ('then do it with the cotlet_browser_* tools in the user's Phorest Cloud Browser'), which is genuine when-to-use guidance. However, it never distinguishes this from adjacent guidance tools such as cotlet_app_guide, offers no explicit exclusions or preconditions, and the API-credential paragraph reads as justification for the wrapper rather than routing guidance.

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