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?
Beyond annotations, the description discloses key behaviors: it provides a browser login link, suggests permanent token storage in config, explains session-only behavior, and specifies the no-args link retrieval. This is rich contextual detail that enhances understanding.
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 slightly dense and run-on, but each segment earns its place, covering audience, two methods, and parameter usage. It could be broken into clearer sentences but is not excessive.
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?
With one optional parameter and no output schema, the description covers all essential aspects: how to authenticate, the two paths (permanent/session), and what happens with no args. It is complete enough for an agent to invoke 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?
The input schema only shows a 'token' string, but the description explains it is a JWT, that it is optional (can omit to get a link), and exactly how to use it in a call. This fully compensates for the 0% schema 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 indicates this tool is for authentication with MCP.AI, providing instructions for obtaining and using a token. However, it lacks a crisp verb+resource statement like 'Authenticates the user' and instead fronts with audience context, so it's clear but not maximally precise.
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 offers explicit guidance on two usage methods (permanent config vs. session-only) and when each is appropriate, but it does not mention alternatives outside this tool or state when not to use it, leaving a slight gap.
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 tools have clearly distinct purposes, but 'authenticate' and 'connect' both relate to authentication/connection status, and 'marketplace' is a sprawling meta-tool that overlaps with many capabilities. The domain-specific 'cnd_municipal_consultar' stands apart from the generic platform tools, reducing confusion among the former but making the set feel disjointed.
Names mix single-word verbs (connect, marketplace), compound verbs (report_bug, show_version), and an inconsistent noun phrase (toolkit_info). The Portuguese 'cnd_municipal_consultar' contrasts sharply with English tool names, and there is no consistent verb_noun pattern across the set.
While 7 tools is a reasonable number, the server is named 'CND Municipal' yet contains only one domain-specific tool; the other six are generic MCP platform utilities. This is a poor match between the server's apparent purpose and its actual tool composition.
For a CND Municipal service, the surface is extremely thin: only one query tool for the actual domain. There are no management operations for CND records, credit balance, or history. The platform tools (marketplace, connect, etc.) do not address domain completeness, leaving significant gaps for any real CND workflow.