Condomínios / Contas bancárias: Estornar movimentação bancária (PUT /movimentacoesDiretas/estornar). [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?
The description explicitly marks the operation as '[write, altera dados]', which complements the annotations by stating in human-readable terms that the tool modifies data. Annotations already indicate readOnlyHint=false, so this is partly redundant, but it adds a useful explicit warning. No further behavioral detail such as reversibility or required permissions is disclosed.
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-loads the domain, action, endpoint, and write-behavior warning in a single sentence. It avoids filler, though it sacrifices some needed detail.
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?
With no output schema, no required parameters, and zero parameter documentation, the description is insufficient for correct invocation. It provides the endpoint and a broad category, but omits request format, parameter meanings, and behavioral caveats.
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 provides zero parameter-level guidance. The three parameters body, query, and account are entirely unexplained, leaving the agent without any clue how to construct a valid request.
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-resource pair: 'Estornar movimentação bancária' (reverse bank transaction), with the exact endpoint PUT /movimentacoesDiretas/estornar. The domain prefix 'Condomínios / Contas bancárias' distinguishes this from sibling tools like superlogica_cobranca_estornar or superlogica_despesas_estornar.
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 is given for when to use this tool versus alternatives. It does not mention other estornar-type siblings or any conditions that would select this tool. The domain label gives only implicit context, not explicit selection criteria.
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.