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 |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate idempotentHint=true, no destructive or readOnly hints. The description adds context beyond annotations: explains the two login modes (permanent vs session) and the browser flow. It does not contradict annotations and adds useful behavioral details.
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 verbose but every sentence provides value. It front-loads the main purpose and uses a colon to separate context from instruction. Could be slightly more terse, but still effective.
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 lack of output schema, the description does not fully describe the return format. It mentions the link but not the response structure. For a simple auth tool, this is adequate but incomplete; a brief mention of the response object would improve completeness.
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 has zero parameter descriptions (schema coverage 0%). The description compensates fully by explaining the 'token' parameter as a JWT and that calling without args returns a login link. This adds essential semantics missing from 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 specifies the tool's purpose: authentication for IDE agents via token. It uses specific verbs ('log in', 'copy', 'paste') and distinguishes from sibling tools which cover different functionalities like connecting, reporting bugs, or managing contracts.
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 guidance on when to use this tool: for permanent config (add to header) or session-only login (call with token). Also explains the alternative of calling with no args to get a link. This clearly differentiates use cases.
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.
Multiple tools are easily confused: person_write_create/person_write_update and sale_write_create/sale_write_update duplicate the same operation with an internal action flag, and authenticate vs connect both deal with connection setup. Also, list_accounts (company installs) and list_financial_accounts (bank accounts) have similar names but different meanings.
Naming patterns vary widely: verb_noun (create_budget, list_people) is mixed with noun_verb (contract_write, person_delete, product_write). The contaazul_ prefix is applied inconsistently, and standalone names like authenticate, connect, marketplace, and toolkit_info break the pattern. Flattened action pairs add redundant, non-idiomatic names.
With 57 tools, this server exceeds the 50+ threshold for an extreme count. The tool list is bloated with generic platform tools (authenticate, marketplace, report_bug) alongside dozens of domain-specific ones, making it overwhelming for agents to parse and select from.
The Conta Azul domain is well represented: people, products, services, sales, budgets, contracts, financial accounts, receivables/payables, settlements, charges, invoices, and transfers all have read/create/list operations, and most have update/cancel/delete. Minor gaps like product update/delete or service update exist due to API limitations, but the core workflows are covered.