Pesquisa notas fiscais (notas.fiscais.pesquisa.php). Paginado. filters (JSON) aceita dataInicial/dataFinal (DD/MM/AAAA), situacao, numeroNota, cpf_cnpj etc.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | ||
| search | No | ||
| account | No | ||
| filters | 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 declare this as read-only, idempotent, and non-destructive, so the safety profile is covered. The description adds useful behavioral details about pagination and supported filter keys/date format, but does not discuss response behavior, limits, or error cases.
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 compact, front-loaded, and easy to scan. The internal endpoint reference, `notas.fiscais.pesquisa.php`, adds little value and slightly reduces clarity, but the overall structure is efficient.
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 read-only listing tool, the description provides enough to understand the basic use case: search invoices with pagination and filters. However, no output format is described, and effectively 3 of 4 parameters are not documented, leaving meaningful gaps for an agent that needs to construct calls reliably.
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 description coverage is 0%, so the description must compensate. It explains the `filters` parameter well, including JSON keys and the DD/MM/AAAA date format, but leaves `search`, `account`, and even `page` semantics mostly undocumented beyond the implication of pagination.
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 that this tool searches invoices (notas fiscais), and mentions pagination and filter options. It is identifiable as a list/search tool, though it does not explicitly differentiate itself from tiny_get_invoice or other listing tools.
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 conveys that the tool is used for paginated invoice searching with filters, which gives reasonable usage context. It does not explicitly state when to prefer this tool over tiny_get_invoice or other list/search alternatives.
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 tiny_* tools are clearly distinct by resource and action, but the generic platform tools blur together: marketplace also handles report_bug, install/uninstall, token/connect links, and toolkit state, overlapping with authenticate, connect, report_bug, and toolkit_info. An agent could easily call marketplace for something a dedicated tool already covers, or confuse connect with authenticate.
The Tiny ERP tools follow a clean verb_noun pattern (tiny_list_orders, tiny_get_product, tiny_create_contact), but the platform tools use short unprefixed verbs (authenticate, connect, marketplace, report_bug, show_version, toolkit_info). Two internally consistent naming schemes coexist, so the overall set feels mixed rather than chaotic.
At 20 tools, the count is borderline heavy and mixes two distinct concerns: Tiny ERP operations and mcp.ai platform administration. The ERP tools are each reasonably scoped, but the generic tools could likely be consolidated, especially marketplace, which already absorbs several capabilities.
The ERP surface is heavily read-oriented: contacts, orders, invoices, products, payables, and receivables all support list/get, but only contacts have a create operation. There are no update/delete operations for any entity and no way to create orders, invoices, or products, which creates significant dead ends for real business workflows.