Return a link to the Stripe billing portal for the signed-in person, where they can change their card, download invoices, or cancel a subscription. Does NOT charge anything and does NOT change anything: it returns a link the person must open themselves. Single-use and short-lived. Requires an OAuth 2.1 user access token.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds critical behavioral details beyond these: 'single-use and short-lived', 'does NOT charge anything', and 'does NOT change anything: it returns a link the person must open themselves'. It also discloses the OAuth 2.1 user access token requirement, which is not implied by 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?
The description is concise and well-structured: it leads with the core purpose in the first sentence, immediately clarifies side-effect absence in the second, and wraps up with security/time constraints in the third. Every sentence adds value with no filler, and the most important information is front-loaded.
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 tool with no parameters, no output schema, and comprehensive annotations (readOnly, idempotent, non-destructive), the description fully covers what an agent needs: what it returns, its single-use nature, short-lived validity, and auth requirements. There are no gaps that could cause incorrect invocation.
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 has zero parameters, and the schema coverage is 100% (empty properties). Since there are no parameters to describe, the description adds no parameter-specific semantics, but the baseline for 0 params is 4 per the rubric. The description's focus on the action and constraints is sufficient; there is nothing missing related to parameters.
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 explicitly states the verb ('Return a link') and the resource ('Stripe billing portal') and clarifies the purpose ('change card, download invoices, cancel subscription'). It distinguishes itself from siblings like purchase_plan (which charges) and get_billing_history (which lists), making the tool's role unmistakable.
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 description gives clear context on when to use the tool (for billing portal access) and notably clarifies that it does NOT charge or change anything, which helps disambiguate from purchase_plan and top_up_balance. It also mentions the OAuth token requirement, guiding on authentication prerequisites. However, it does not explicitly name sibling alternatives or provide conditions for when not to use it beyond its non-destructive nature.
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.
The set contains several near-neighbor groups: deprecated aliases duplicate live tools, and docs/billing/financial tools have fuzzy boundaries. Individual descriptions are detailed and resolve most collisions, but matching the right tool among 39 still requires care.
Most tools follow a sensible verb_object style, but the transcribe_* group is inconsistent: transcribe_url/transcribe_upload are verb_object, while transcribe_status/transcribe_cancel/transcribe_delete are really status/cancel/delete operations renamed with a transcribe prefix. The deprecated transcription_status/transcription_url aliases add another naming convention, so the pattern is not reliable across the set.
39 tools is well over the 25+ threshold and creates an overwhelmingly broad surface spanning account management, billing, docs, API jobs, library organization, meeting bots, and automations. Two deprecated duplicates inflate the count further. This would be more coherent split into separate servers or at least pruned of deprecated aliases.
Core API transcription lifecycle is covered, and the library/meeting-bot flows have search, tagging, moving, and audio retrieval. However, there is no user-library deletion/rename, no OAuth-side full-transcript access, local upload is non-functional over the hosted endpoint, and webhook management is documented but not exposed as tools. These gaps force agents to work around missing operations.
