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 and destructiveHint=false, which the description does not contradict. The description adds behavioral context: calling with no args returns a link, while calling with a token performs session login. It also explains the token is a JWT and distinguishes permanent vs session connections. This goes beyond annotations by detailing the auth flow and token format.
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 block of text but is well-structured with clear alternatives (config vs session) and invocation modes. It includes necessary context for IDE agents without being overly verbose. Every sentence contributes to understanding the tool's usage, though it could be slightly tightened without losing value.
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 tool is simple (one optional param, no output schema) and the description covers both permanent and session auth paths, including token format and link retrieval. It does not explicitly describe the return value, but the phrase 'get the link' implies it. Overall, it provides sufficient context for an agent to invoke the 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?
Although schema coverage is 0%, the description gives clear meaning to the single optional 'token' parameter: it is a JWT that can be pasted for session login. It also explains that omitting it triggers a link request. This fully compensates for the lack of schema docs and provides semantic value beyond the bare type 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 clearly states the tool's purpose: authenticating the user by logging in via browser and obtaining an access token. It distinguishes itself from siblings by focusing on the authentication flow, and it specifies the resource (access token) and the action (log in). The verb 'authenticate' is specific and the description elaborates on the mechanism.
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 provides explicit when-to-use instructions: either add the token to the server's config for permanent access, or paste it for session-only login. It also explains the two invocation modes (with token or no args). It clearly states how the tool fits into the authentication workflow, even if it doesn't explicitly exclude sibling tools.
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.
Every tool has a clearly distinct purpose: authenticate handles credentials, connect checks status, marketplace searches/invokes MCPs, report_bug sends feedback, show_version displays version info, toolkit_info shows installed MCPs, and sema_mt_apf_consultar performs the actual domain query. There is no overlap or ambiguity between them.
Tool names follow mixed conventions: some are plain verbs (authenticate, connect), some are nouns (marketplace, toolkit_info), some are verb-noun (report_bug, show_version), and one is in Portuguese with a domain prefix (sema_mt_apf_consultar). This inconsistency makes naming patterns unpredictable.
Seven tools is a reasonable count for this server, but six of them are generic platform utilities (auth, connection, diagnostics, marketplace) while only one is domain-specific. The count is appropriate, though the balance feels slightly off given the server's stated purpose appears to be a specific APF Rural consultation.
The domain surface is a single consultation endpoint, which is fully covered by sema_mt_apf_consultar. There is no obvious missing CRUD operation because the domain is inherently read-only. However, the toolkit lacks any domain-specific history, batching, or additional query capabilities, which could be considered a minor gap if more granular interactions were expected.