Manage browser sessions by listing, retrieving, or clearing cookie metadata per domain. Filter by name or frame to check expiry, httpOnly, and secure status without exposing values.
Cookie session manager: action:"list" (metadata for a url domain — names, expiry, httpOnly, secure; NO values)…
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| name | No | ||
| action | No | ||
| frameId | No | frameId (omit=top) |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full disclosure burden. It does disclose one meaningful trait: list returns metadata only and explicitly no cookie values. But it is silent about the clear/clear_all actions being destructive, about side effects on the session, or any auth/permission requirements, leaving a large transparency gap.
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 short sentence is compact, but the trailing ellipsis signals truncation, and the multi-action tool deserves at least a structured summary. It under-specifies rather than being efficiently concise.
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 4 parameters, an action enum of 4 values, no output schema, and no annotations, this description is far from complete. It documents only one action and leaves the other three, the output shape, and edge cases undefined, so an agent cannot reliably invoke the 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?
Schema coverage is only 25% (frameId), and the description does not explain the required url parameter, the name parameter, or the action enum beyond the list case. It adds no meaning for get/clear/clear_all, so an agent cannot infer how to fill the parameters for those actions.
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 (cookies) and specifies the list action's output (metadata with names, expiry, httpOnly, secure, and NO values), so an agent knows the tool is cookie-related and what list returns. However, it doesn't mention the get/clear/clear_all actions or distinguish from sibling tools like session, so it's clear but not fully differentiated.
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?
There is no when-to-use guidance or mention of alternatives. The text focuses only on what list returns; it does not say when to use cookies instead of session, network_log, or other sibling tools, nor when get/clear are appropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.