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 indicate idempotentHint=true but no destructive behavior. The description adds context about browser login, token copying, and the distinction between permanent and session-based auth. It doesn't contradict annotations and adds useful behavioral detail about the authentication flow, though it could mention what happens on successful/failed auth.
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 paragraph but logically organized: first the purpose, then the recommended permanent method, then the session alternative. It's slightly verbose with the phrase 'MCP.AI for IDE agents' which is context, but not wasted. Could be tightened slightly but remains clear.
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 (1 optional param, no output schema), the description fully covers the authentication flow, including the two usage modes and the role of the token. It also implicitly explains why an agent would call this tool (to get a link or send a token). No gaps remain.
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 has one param 'token' with no description (coverage 0%). The description fully explains the parameter: it's a JWT that can be passed for session login, and that calling with no args returns a link. This provides complete semantics beyond the schema.
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 purpose: authentication for MCP.AI IDE agents, with specific instructions for obtaining an access token. It distinguishes between permanent (config header) and session-only (token argument) modes, making it distinct from the sibling tools which are all Google Ads operations.
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?
Explicitly explains two workflows: adding a header for permanent connection vs. pasting a token for session-only. It also specifies exactly what to call with arguments (`{ token: ... }`) and without args (get link), leaving no ambiguity on when and how to use the tool.
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 google_ads_* tools map to distinct resource+action pairs, but the five keyword tools (keywords_keywords, keywords_diagnostics, keywords_raw, keywords_search_terms, keywords_status) share essentially the same description and action list, differing only by a flattened action label. google_ads_account, google_ads_status, google_ads_list_accounts, and connect/toolkit_info also overlap in account/status purposes.
Domain tools mostly follow a google_ads_<resource>_<action> pattern, with plural nouns for list operations like google_ads_campaigns and google_ads_ads. This is muddied by redundant google_ads_keywords_keywords, metric-only names like google_ads_roas/google_ads_today, and six generic meta tools that break the prefix pattern.
35 tools is too many for a coherent Google Ads surface. Five keyword tools are one logical action router split into separate endpoints, and several platform tools (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) are unrelated to the Google Ads domain, inflating the count.
The server covers major workflows: accounts, campaigns, budgets, ad groups, ads, keywords, negative keywords, sitelinks, performance, and change history. However, there is no way to list existing ad groups, no negative keyword removal, and no creative update beyond pause/enable/remove, which are notable gaps for this domain.