cotlet_browser_closeEnds the browser session when the task is done: the browser keeps its cookies and sleeps, and the per-minute charge stops. Answers the session's minutes and credits.
| Name | Required | Description | Default |
|---|---|---|---|
| app | No | Leave it out: the step runs in the user's web browser. Only when cotlet_app_guide names an app's own Cloud Browser, that app's slug, e.g. milanote. |
Changes observed during successful MCP inspections.
Input schema / properties / app / descriptionPrevious value: -"Slug of a connected app, e.g. milanote: the step runs in that app's Cloud Browser, signed in as the user and kept to the app's site. Leave it out for the user's web browser, also for an app without its own Cloud Browser."New value: +"Leave it out: the step runs in the user's web browser. Only when cotlet_app_guide names an app's own Cloud Browser, that app's slug, e.g. milanote."Input schema / properties / app / descriptionPrevious value: -"Slug of a connected app, e.g. milanote: the step runs in that app's Cloud Browser, signed in as the user and kept to the app's site. Leave it out for the user's web browser."New value: +"Slug of a connected app, e.g. milanote: the step runs in that app's Cloud Browser, signed in as the user and kept to the app's site. Leave it out for the user's web browser, also for an app without its own Cloud Browser."Input schema / properties / app / descriptionPrevious value: -"Slug of an app the user enabled for agents, e.g. milanote: the step runs in that app's Cloud Browser, signed in as the user and kept to the app's site. Leave it out for the user's web browser."New value: +"Slug of a connected app, e.g. milanote: the step runs in that app's Cloud Browser, signed in as the user and kept to the app's site. Leave it out for the user's web browser."Input schema / properties / appAdded value: +{
+ "description": "Slug of an app the user enabled for agents, e.g. milanote: the step runs in that app's Cloud Browser, signed in as the user and kept to the app's site. Leave it out for the user's web browser.",
+ "pattern": "^[a-z0-9][a-z0-9-]{0,79}$",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only give generic safety hints (non-read-only, non-destructive, idempotent); the description adds real behavioral detail beyond them — cookies persist, the session sleeps rather than being destroyed, per-minute billing stops, and the call returns minutes and credits. None of this contradicts the annotations.
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?
One sentence, front-loaded with the action and timing, followed by the state/billing consequences and the return value. Every clause earns its place.
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 one-optional-parameter lifecycle tool with no output schema, the description covers timing, side effects on session state, billing impact, and what the call returns. Nothing an agent needs to call it correctly is missing.
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 description coverage is 100% and the single `app` parameter is fully documented in the schema, so the description carries no burden here. It does not mention the optional app targeting at all, so baseline 3 applies.
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?
"Ends the browser session" is a specific verb+resource, and the description scopes it to "when the task is done." It is clearly the counterpart to cotlet_browser_open, though it never names the sibling explicitly.
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?
The trigger condition ("when the task is done") tells the agent exactly when to call it and implies it should not be called mid-task. No explicit when-not or named alternatives, but the context is unambiguous for a close operation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.