create_tagCria uma nova tag para marcar transações do usuário autenticado. Não valida duplicidade de nome.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Nome da tag | |
| color | No | Cor da tag (ex: hex '#RRGGBB') |
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | ||
| name | No | ||
| color | No | ||
| userId | No | ||
| createdAt | No | ||
| updatedAt | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / properties / color / descriptionAdded value: +"Cor da tag (ex: hex '#RRGGBB')"Input schema / properties / name / descriptionAdded value: +"Nome da tag"Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as non-read-only, non-idempotent, and non-destructive. The description adds a non-obvious behavioral caveat: 'Não valida duplicidade de nome', which tells the agent duplicate names are allowed and not rejected. It also scopes the operation to the authenticated user's transactions.
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?
Two short sentences in Portuguese, front-loaded with the action and followed by the one caveat that matters. No filler or redundancy.
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?
For a simple two-parameter creation tool with output schema and safety annotations, the description covers the essential behavior. It could additionally direct the agent to list existing tags when uniqueness matters, but that is a usage-guidance enhancement rather than a blocker.
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?
With 100% schema coverage, the schema already documents both parameters. The description adds one meaningful parameter-related fact: the `name` field is not validated for duplicate, so the agent should not assume uniqueness. This goes beyond the schema's plain type/description.
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 uses a specific verb and resource: 'Cria uma nova tag para marcar transações do usuário autenticado.' It clearly identifies what is created and for whom, and the resource 'tag' distinguishes it from sibling tools like create_category and create_transaction.
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?
No guidance on when to prefer this tool over alternatives is given. It does not mention checking existing tags with list_tags before creating, nor any condition that would rule this tool out. The duplicate-name warning is behavioral, not usage routing.
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 tools are individually well-described and many cross-reference their closest neighbors, but the set contains several easily confused clusters: create_transaction/confirm_new_transaction, update_equity/add_equity_valuation, the invoice tools (current_invoice, next_invoice, list_pending_invoices, get_invoice), and the many analytics/projection tools. The descriptions help a careful reader, but with 81 tools an agent is likely to misselect among these overlapping surfaces.
CRUD operations consistently use create_/list_/update_/delete_ plus a resource noun, and all names are snake_case. However, there is a large second group of noun-phrase analytics tools (cashflow_forecast, spending_projection, categories_insights, transport_routine) plus one-off verbs such as can_afford, pay_invoice, and validate_current_invoices, so the naming convention is mixed even though it remains readable.
81 tools is far beyond the practical MCP tool surface and exceeds the rubric's 50+ extreme-mismatch threshold. Even if each tool maps to a real finance endpoint, the volume overwhelms an agent's context window and makes selection much harder.
The server covers the finance lifecycle extensively: accounts, cards, invoices, transactions, recurring rules, budgets, goals, debts, equities, categories, tags, cost centers, profile, projections, and insights all have working read/write paths. Minor gaps remain, such as no update/delete for tags and no direct update/delete for system-generated invoices, but agents can usually work around these.