ausca_browser_session_closeIdempotently terminate the CDP relay and upstream browser for one lease. Closing never creates another payment. Supply the lease bearer on the HTTP or MCP transport; never place it in tool arguments.
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| status | Yes | ||
| session | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the annotations' destructive and idempotent hints, the description states what is destroyed (CDP relay and upstream browser), adds a critical side-effect guarantee ('Closing never creates another payment'), and explains that the lease bearer belongs on transport, not in tool arguments. No statement 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?
Three short sentences front-load the action and add only high-value behavioral and security context. No sentence is redundant with the title or schema.
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-parameter, clearly annotated close action with an output schema, the description plus annotations cover the essential behavior, side effects, and auth placement. Minor gaps remain around error behavior and where the session_id comes from, but these are not blocking.
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 only parameter, session_id, has no property description in the schema, and the description never explicitly explains that session_id is the lease identifier or how to obtain it. It does add one valuable semantic warning—do not place the lease bearer in tool arguments—which prevents a common misuse. With 0% schema coverage, this partial compensation is useful but incomplete.
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 uses a specific action ('terminate') and names the exact resources affected ('CDP relay and upstream browser'), scoped to 'one lease.' This makes it unambiguous and easily distinguishable from the connect and status siblings, which create/attach or inspect sessions.
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 implies the tool is for ending an existing lease and is safe to call repeatedly ('idempotently'), and it gives concrete transport-level instructions for supplying the lease bearer. It does not explicitly name alternatives or when not to use it, so it stops short of full routing guidance.
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.
Each tool targets a clearly separate operation within its domain: inbox read/list/attachment/status/delete are all distinct, browser connect/status/close are unambiguous, and offer/invocation tools each have unique responsibilities. Descriptions reinforce the boundaries, so an agent should not struggle to select the right tool.
Naming is divided into two patterns: resource-first names like ausca_agent_inbox_read and ausca_browser_session_close, versus verb-first names like ausca_get_invocation and ausca_search_offers. Within the inbox and browser groups, endings mix nouns (messages, status, attachment) and verbs (delete, read, connect), making the convention inconsistent across the set.
13 tools is well within the ideal range for a multi-domain server, and each tool covers a meaningful operation without redundancy. The count supports inbox, browser session, and offer/invocation workflows without feeling bloated or sparse.
The inbox and browser-session clusters cover their core lifecycles well, and the offer/invocation cluster supports search, detail, preparation, state read, and cancellation. The main gap is the lack of an explicit submit/execute invocation tool, though invocation submission may be intentionally externalized; this is a minor workaround rather than a fatal dead end.