list_api_keysLists all API keys for the current user. Returns key metadata (prefix, name, scope, dates) but never the raw key. Requires admin scope.
| Name | Required | Description | Default |
|---|---|---|---|
| access_token | No | Optional bearer token; prefer session_request_id. | |
| session_request_id | No | Session handle from create_auth_session; pass it on every authenticated call. |
| Name | Required | Description | Default |
|---|---|---|---|
| keys | No | ||
| count | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool read-only, idempotent, and non-destructive. The description adds meaningful behavior beyond those hints: it returns only metadata (prefix, name, scope, dates), never the raw key, and requires admin scope. This is useful context for an agent deciding whether the call satisfies a request.
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 three short sentences with no filler. It front-loads the core action, then supplies the key behavioral caveat and the admin-scope requirement. Every sentence 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?
Given that an output schema exists (so return value details are handled elsewhere) and annotations cover safety, the description provides the remaining necessary context: current-user scope, admin requirement, and the fact that raw keys are never exposed. Nothing essential is missing for an agent to invoke this tool correctly.
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%, so both parameters (access_token and session_request_id) are already well-documented in the input schema. The description does not add parameter-specific semantics, but with full schema coverage the baseline score 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?
States a specific verb and resource: 'Lists all API keys for the current user.' It also clarifies that raw keys are never returned, which distinguishes it from key-creation or key-revocation siblings. The scope (current user) and metadata-only behavior make the tool's purpose unambiguous.
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 implies usage when you need to enumerate API keys, but it does not explicitly name alternatives like create_api_key or revoke_api_key, nor does it state when not to use this tool. The admin-scope requirement and current-user context provide some guidance, but routing is left to inference.
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.
Most tools map cleanly to distinct resource-action pairs (displays, organizations, assets, data slots, store templates, auth). A few clusters like the get_store_template_* family and the auth/session tools could still confuse an agent, but their descriptions are explicit enough to separate them.
The dominant pattern is consistent verb_noun snake_case (list_*, get_*, create_*, delete_*, send_*, set_*, manage_*). Deviations like fetch, search, authenticate, logout, and pair_by_code are understandable but break the otherwise uniform naming scheme.
With 57 tools this server far exceeds the 50+ threshold, creating an extreme tool-set size for an MCP server. Even though the underlying platform is feature-rich, the sheer number of tools heavily taxes context and selection.
The surface covers display, organization, asset, data slot, store template, auth, API key, and licensing lifecycles in impressive depth. Minor gaps exist, such as no delete operation for display categories and no reboot/power control for displays.