Model Context Protocol (MCP) server for FinGo: construction budget lookup, official Caixa/IBGE SINAPI database for all 27 Brazilian states, and construction financial
Scored across 3 tools
Each tool serves a clearly distinct purpose: financial summary, SINAPI database lookup, and plan comparison. There is no overlap or ambiguity between them.
All tools follow a consistent verb_noun snake_case pattern (get_financial_summary, get_sinapi_info, search_plans). The naming is predictable and uniform.
With only 3 tools, the set is on the lean side but still fits the narrow scope of the server (financial summaries, cost reference data, and plan comparison). It avoids bloat while covering the core advertised functionality.
The tools provide a read-only overview of financial health, external cost data, and plan features, but lack deeper operations such as detailed cash flow breakdowns, cost center drill-downs, or any update/create/delete capabilities. While acceptable for a query-focused server, notable gaps exist for more comprehensive workflows.
Retorna o resumo executivo de saúde financeira, fluxo de caixa e centros de custo de obras no FinGo.
| Name | Required | Description | Default |
|---|---|---|---|
| obra_id | No | Identificador opcional da obra para filtragem analítica de centro de custo. |
| Name | Required | Description |
|---|---|---|
| summary | No | Resumo executivo de contas a pagar, receber, saldo e DRE. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already signals that this is a safe read operation, and the description's 'Retorna' is consistent with that. It adds useful context about what data is returned, but it does not disclose additional behavioral traits such as authentication needs, data freshness, or response behavior beyond the output schema.
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 front-loaded sentence with no filler or redundant phrasing. Every word earns its place, and the core resource is stated immediately after the verb.
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 tool with one optional, fully documented parameter and an output schema, the description covers the invocation essentials. It is not quite complete because it leaves when-to-use and sibling routing implicit, but nothing critical is missing for making the call.
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 100%, and the obra_id parameter already has a clear description: 'Identificador opcional da obra para filtragem analítica de centro de custo.' The tool description adds no additional parameter meaning, so the baseline of 3 is appropriate.
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 opens with the verb 'Retorna' and names a specific resource: an executive summary of financial health, cash flow, and cost centers for construction projects in FinGo. That is clear enough on its own, but it never explicitly differentiates itself from siblings like get_sinapi_info or search_plans.
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?
There is no guidance about when to choose this tool over get_sinapi_info or search_plans, nor any mention of exclusions or prerequisites. The only usage hint is the optional obra_id filter, and the description itself gives no contextual direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Consulta a cobertura e base de dados oficial SINAPI (Caixa Econômica Federal e IBGE) para os 27 estados do Brasil.
| Name | Required | Description | Default |
|---|---|---|---|
| state | Yes | Sigla da Unidade Federativa com 2 letras (ex: SP, RJ, MG, SC, PR, DF). | |
| desonerado | No | Se true, consulta o regime com desoneração da folha (CPRB 4,5%). Se false, não desonerado. |
| Name | Required | Description |
|---|---|---|
| state | No | Estado brasileiro consultado. |
| coverage | No | Detalhamento e referencial legal da base SINAPI disponível. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already declares the tool is safe, and the description does not contradict it. The description adds source/scope context (official SINAPI data, 27 states) but does not disclose further behavior such as pagination, filtering behavior, or access constraints. With annotations present, this is adequate but not rich.
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 front-loaded sentence that states the action, resource, and scope without filler. It is concise and every word contributes to the core purpose.
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 read-only annotation, a 100% documented two-parameter schema, and an output schema, the description is nearly complete for selecting and invoking this tool. It clearly identifies the resource and scope; only the meaning of 'coverage' and explicit usage conditions are left implicit.
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 100%: both state and desonerado are fully documented in the input schema. The description itself adds no parameter-level meaning, but because the schema carries the full burden, the baseline of 3 is appropriate.
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 a specific action ('Consulta' – queries) and resource (SINAPI coverage and official database from Caixa/IBGE), scoped to the 27 Brazilian states. It is specific enough to be distinguishable from the unrelated siblings, though it does not explicitly contrast itself with them.
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 usage guidance is provided. The description does not mention when to use this tool versus get_financial_summary or search_plans, nor does it state any exclusions or alternatives. The only implicit cue is the SINAPI scope, which is not enough to guide selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Pesquisa e compara os planos comerciais, capacidades e recursos do FinGo (Básico, Profissional, Construtora Ilimitado).
| Name | Required | Description | Default |
|---|---|---|---|
| plan_name | No | Nome do plano desejado (ex: 'basico', 'profissional', 'ilimitado') ou 'all' para todos os planos. |
| Name | Required | Description |
|---|---|---|
| plans | No | Lista de planos encontrados com detalhes de recursos, capacidade de obras e preços. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, and the description's 'search and compare' wording is consistent with a read-only operation. The description adds useful scoping about what content is covered (Básico, Profissional, Construtora Ilimitado) but does not disclose additional behavioral details such as output shape or pagination; the output schema reduces the need for those 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 a single, focused sentence with no filler or repetition. It front-loads the action and resource, then names the exact plans, making it very efficient for an agent to parse.
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 search tool with one optional parameter, a readOnly annotation, and an output schema, the description is largely complete. The only minor gap is that no explicit usage guidance is given relative to sibling tools, but the domain is distinct enough that this does not materially hurt 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?
Schema description coverage is 100%, so the single parameter plan_name is already fully documented with examples and the 'all' option. The tool description does not add parameter-level meaning beyond what the schema provides, so the baseline of 3 applies.
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 names a specific action ('Pesquisa e compara') and a concrete resource (FinGo commercial plans, capabilities, and resources), listing the plan names. This clearly distinguishes it from the siblings get_financial_summary and get_sinapi_info, which target different domains.
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 makes it clear this tool is for searching and comparing FinGo plans, which gives an agent strong contextual guidance for when to invoke it. It does not explicitly mention alternatives or exclusions, but the sibling names and the description's domain focus make the usage context unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_financial_summaryget_sinapi_infosearch_plans
Add one secure layer between your agents and this server.