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 declare mutation, idempotence, and non-destructive nature. The description adds valuable context about permanence (non-expiring via config vs session-only) and the two-step workflow. It does not contradict annotations, and the added details are useful but not exhaustive (e.g., no mention of exact return values or failure modes).
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 dense sentence but remains efficient, covering all key points without fluff. It is front-loaded with relevance and packs multiple instructions into a compact form. Slightly long but not wordy; could be split for readability, but maintains conciseness.
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 the tool's simplicity and absence of an output schema, the description adequately covers the workflow: how to invoke, what the no-args call returns (a link), and the two authentication modes. It does not describe error handling or explicit success responses, but for a simple auth tool this is sufficient.
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 defines an optional 'token' string with no description. The tool description fully clarifies that 'token' is the JWT from the browser, and explains that omitting it yields the login link. This completely compensates for the 0% schema description coverage.
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 states the tool's purpose: authentication for IDE agents. It explains the flow of logging in via browser and obtaining an access token, and distinguishes itself from sibling tools by being the sole authentication entry point. The verb 'authenticate' plus the explicit context makes it 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?
Provides explicit usage patterns: call with no args to get a login link, then call with the token after the user pastes it. It also recommends a permanent config-based approach versus session-only, giving clear guidance on when to use each mode. This is more prescriptive than typical tool descriptions.
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 CRM tools are mostly distinct (CRUD, file operations, schema management), but there is potential confusion between crm_describe, crm_get_object, and crm_list_objects, and between crm_upload_file/crm_upload_from_url/crm_confirm_upload. However, descriptions clarify these somewhat. The set also includes auxiliary tools (authenticate, connect, marketplace, etc.) that are clearly separate.
Most tools follow the crm_verb_noun pattern (crm_create_records, crm_delete_records, crm_update_records, etc.). Some deviations like authenticate, connect, toolkit_info, and show_version lack the crm_ prefix, and bulk support is noted in descriptions but not in names. Still, the convention is fairly consistent.
With 36 tools, the count is on the heavier side. The CRM-specific tools (about 27) cover CRUD, schema, relationships, files, and usage, which is reasonable for a full CRM API. However, the inclusion of platform-level tools (marketplace, report_bug, show_version, toolkit_info) adds breadth that goes beyond CRM-specific functionality, making the set feel larger than necessary.
The tool surface is quite complete: full CRUD for records, objects, fields, files, relationships, search, and usage. The descriptions mention validations and bulk support, and the crm_describe tool prompts agents to understand schema first. Gaps are minimal—for instance, no explicit bulk delete for records but crm_delete_records supports bulk via ids. Overall, the domain is well-covered.