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 establish readOnlyHint=false, destructiveHint=false, and idempotentHint=true, so the safety profile is known. The description adds behavioral context beyond annotations by explaining the browser login flow, token permanence vs session-only scope, and no-arg behavior. It does not describe error cases or response format, but it covers the key interaction patterns.
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 longer than average but every segment adds information: login method, permanent config option, session-only option, and no-arg behavior. It is well-structured with 'Best' and 'Or' markers, though slightly dense and could be tightened.
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?
The description covers invocation scenarios and the no-arg link behavior, but there is no output schema and the description does not specify what the tool returns when a token is passed, such as success/failure indicators or session details. For a tool with a nontrivial interactive flow, this is a notable gap.
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 coverage is 0%, but the description fully explains the one parameter: token is a JWT pasted 'after the user pastes', and omitting it triggers the link-return behavior. This compensates completely for the bare schema definition.
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: authenticate/login for IDE agents via browser token exchange. It clearly distinguishes itself from siblings like report_bug and show_version by explaining the login workflow rather than generic tooling.
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?
It gives explicit when-to-use guidance: prefer adding the token to server config for permanent access, or paste the token for session-only login, or call with no args to get the login link. This is strong routing guidance with alternatives clearly stated.
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 twelve busca_google_* tools are each tied to a distinct Google vertical, so selecting the right one for a search task is usually straightforward. The only real ambiguity is between busca_google_lugares and busca_google_mapas, and between authenticate/connect, but the descriptions do clarify their different use cases.
The core search tools follow a highly consistent busca_google_<category> snake_case pattern in Portuguese. However, the six platform-management tools use generic English names like authenticate, connect, marketplace, and toolkit_info, creating a mixed convention across the set.
At 18 tools, the server is in the borderline-heavy range. The 12 search tools are individually justified, but the inclusion of 6 unrelated platform/metadata tools makes the overall count feel inflated for a server titled 'Buscador Google'.
The search surface is impressively broad: web, news, images, videos, shopping, academic, patents, places, maps, reviews, suggestions, and page reading are all covered. Minor niche Google surfaces like Trends or Books are absent, but core search workflows have no dead ends.