Prestação de contas: Adicionar relatórios numa prestação de contas (POST /relatoriosselecao/put). [write, altera dados]
| Name | Required | Description | Default |
|---|---|---|---|
| body | No | ||
| query | No | ||
| account | 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 establish readOnlyHint=false and non-destructive behavior. The description adds that this is a write operation that alters data and specifically adds reports, which is useful. However, it does not disclose consequences like duplicates, idempotency, authentication needs, or side effects. This is acceptable 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 compact and front-loaded with the domain and action, includes the endpoint, and flags the write behavior. There is slight redundancy in repeating 'prestação de contas', but overall the description is concise and has no filler.
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?
The tool has three opaque parameters, no output schema, and no parameter documentation, so the description is far from sufficient for correct invocation. It explains the high-level purpose but not how to construct a request, what account refers to, or what response to expect.
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%, and the description does not compensate at all. The three parameters (body, query, account) are opaque strings; the description gives no indication of what values, formats, or structures each accepts. This is a critical gap for an agent trying to invoke the tool.
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 states a specific verb and resource: 'Adicionar relatórios numa prestação de contas' and gives the endpoint. It clearly conveys what the tool does, though it does not explicitly differentiate itself from the sibling superlogica_relatoriosselecao_put_update beyond the create/update naming.
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 provides no guidance on when to use this tool versus alternatives, such as superlogica_relatoriosselecao_put_update or superlogica_relatoriosselecao_list. The domain label and 'Adicionar' imply one use case, but there are no conditions, exclusions, or explicit routing to the right sibling.
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.
Many tools have overlapping boundaries: arquivos_create vs arquivos_put both add files, configuracoes_list vs configuracoes_list_get vs ini_config are three config-listing variants, and sindicos_list vs sindicos_list_get vs responsaveis_list vs usuario_list are four person-listing tools with similar semantics. The recurring _list vs _list_get suffix pattern across resources (inadimplencia, planocontas, configuracoes, sindicos) makes selection genuinely ambiguous.
The superlogica_<resource>_<action> prefix is consistent, but action verbs are a chaotic mix of English (create, delete, update) and Portuguese (desfazer, estornar, liquidar, desinvalidar), and HTTP-method suffixes are semantically inverted (malotes_put creates while malotes_post edits; despesas_post edits). Platform tools (authenticate, marketplace, toolkit_info) break the pattern entirely, and there is a typo in ocorrencias_susgestoes.
120 tools is an extreme count, far beyond the 50+ threshold for a mismatch. Even granting the breadth of a condominium-management domain, the surface looks like an uncurated endpoint-by-endpoint dump of the entire Superlógica API rather than a designed tool set.
The core domain is remarkably well covered: receitas, despesas, acordos, cobranças, unidades, condomínios, ocorrências, reservas, tickets, processos judiciais, and relatórios all have substantial lifecycle coverage including create/edit/delete/liquidar/estornar operations. Minor gaps exist (no delete for fornecedores or comunicados, no get-by-id for condominios/cobrancas, no ticket status update), but agents can work around most of them.