portkey_list_virtual_keysList virtual keys (the aliases that map to provider credentials + budget/rate limits used in requests). Portkey: GET /virtual-keys.
| Name | Required | Description | Default |
|---|---|---|---|
| page_size | No | Number of records per page. Default 50. | |
| current_page | No | Page number (0-based) for pagination. Default 0. |
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?
Annotations declare readOnlyHint=true, and the description adds context about what the virtual keys represent and the REST endpoint. It does not disclose additional behavioral details beyond the annotation, but for a simple read-only list operation this is sufficient.
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 a single focused sentence that front-loads the action and then provides a clarifying definition and endpoint. There is no filler or redundancy.
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 simple read-only list tool with two optional pagination parameters and no output schema, the description covers the essential purpose and object semantics. It might optionally mention that it returns a paginated list, but the schema already documents pagination, so nothing critical 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%, with both parameters (page_size and current_page) already documented with defaults and types. The description adds no parameter-specific detail, so the baseline of 3 is appropriate.
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 states a specific verb and resource: 'List virtual keys', and elaborates with a parenthetical definition of what virtual keys are (aliases mapping to provider credentials plus budget/rate limits). This clearly distinguishes it from sibling tools like portkey_get_virtual_key (singular) and other list tools.
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 usage context is implied by 'List virtual keys' — an agent can infer this is the tool to call when enumerating virtual keys. However, there is no explicit guidance on when to choose this over alternatives such as portkey_get_virtual_key, nor any exclusions or prerequisites.
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.
Every tool targets a distinct resource or analytics operation; the list/get pairings are standard and clearly separated by resource type. No two tools appear to do the same thing.
All tools follow a consistent portkey_<verb>_<resource> pattern using snake_case. The verbs are limited to list, get, and create, and the resource names are consistently ordered.
Sixteen tools is slightly above the ideal 3-15 range, but each tool maps to a distinct resource or endpoint and none feel redundant. The count is manageable for an admin/observability server.
The read surface is strong: every major resource has list and get coverage, plus analytics and feedback logging. The main gap is the lack of create/update/delete operations for most managed resources, but for an inspection-focused tool this is a workable limitation.