MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header Authorization: Bearer <token> for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "" } after the user pastes, or with no args to get the link.
| Name | Required | Description | Default |
|---|---|---|---|
| token | No |
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 already indicate idempotent and non-destructive behavior, and the description adds useful context: login happens in the browser, configured tokens are non-expiring, pasted tokens are session-only, and calling with no args returns a link. It does not specify return values, but this is minor given the simple workflow.
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 compact and front-loaded with the core action and best practice. The 'MCP.AI for IDE agents' opener is mildly extraneous, but every subsequent sentence contributes meaningful usage information.
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 one optional parameter and no output schema, this description covers all relevant invocation modes and the permanent versus session-only distinction. It could go further on expected response/error behavior, but the essential context for an agent to help a user authenticate is present.
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 schema only declares an optional string 'token' with no description, so the description must compensate. It does so by explaining that token is a JWT to be pasted, that omitting it returns a login link, and that using a configured header is the recommended permanent path.
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 clearly identifies the action (authenticate/log in), the resource (access token for the MCP server), and the browser-based flow. It is specific enough to distinguish itself from the domain-specific sibling tools, as it is the only tool concerned with authentication and token exchange.
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 explicit guidance on when to use the permanent config-header approach versus the session-only pasted-token approach. It also clearly states when to call with a token and when to call with no arguments to get a login link.
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.
Many tools are near-duplicates, such as iclips_financial_entries_get/list, iclips_pieces_get/list, iclips_pieces_write_create/update/checklist, and iclips_workflow_templates_get/list, all sharing essentially the same description. authenticate and connect also overlap on session/connection status, so an agent must rely on brittle naming conventions rather than clear semantic boundaries.
The iClips tools mostly follow iclips_<resource>_<action>, but the server mixes noun-only names like iclips_financial_accounts and marketplace, camelCase platform names like toolkit_info and show_version, and artificial get/list flattened duplicates. The pattern is only predictable within a subset of the tool list, not across the entire server.
At 30 tools, the set is over-inflated for its actual scope: most are flattened get/list or write-action variants of roughly a dozen underlying iClips operations, plus six unrelated platform utilities. The domain could be cleanly served in about half this many tools without losing functionality.
Jobs and pieces have reasonable CRUD coverage, but there is no client/group or destination master lookup even though clientId is required to create a job and destination_id filters financial entries. Job pieces and tasks also lack delete operations, and financial categories are not enumerable, leaving noticeable dead ends for common workflows.