Lista/busca processos. Filtros úteis: numero, nome_parte, cpf, cnpj, advogado_nome, status, comarca, uf, data_inicio, data_fim, movimentacao, dias_movimentacao. Demais filtros via query.
| Name | Required | Description | Default |
|---|---|---|---|
| uf | No | ||
| cpf | No | ||
| cnpj | No | ||
| page | No | ||
| query | No | ||
| numero | No | ||
| status | No | ||
| comarca | No | ||
| data_fim | No | ||
| page_size | No | ||
| nome_parte | No | ||
| data_inicio | No | ||
| movimentacao | No | ||
| advogado_nome | No | ||
| dias_movimentacao | 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 readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value by listing available filters and the catch-all 'query' parameter, but it does not disclose pagination, response format, or default behavior. No contradictions with annotations.
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 main purpose, followed by a concise list of filters. It contains no redundant or filler content, making every sentence earn its place.
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 tool's 15 parameters, nested query object, and lack of output schema, the description covers the main filters but omits pagination, parameter combination rules, and result behavior. It is adequate for a list tool but not fully detailed for more complex usage.
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?
The input schema has 0% description coverage, so the description compensates by explicitly listing 12 of 15 parameters as useful filters and introducing the 'query' object for additional filters. Pagination parameters (page, page_size) are not mentioned, and formats are unspecified, but the description adds significant semantic meaning.
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?
Description clearly states 'Lista/busca processos' (verb+resource) and enumerates a list of useful filters, reinforcing its role as a search/list tool. This distinguishes it from single-process tools like easyjur_get_processo, though it does not explicitly name alternatives.
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 implies usage for listing/searching processos with the provided filters, but gives no explicit when-to-use or when-not-to-use guidance. The 'Demais filtros via query' line offers some direction, but no exclusions or comparisons to sibling list tools are provided.
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.
Each tool targets a distinct resource or sub-resource with clear CRUD actions. The easyjur_ tools are separated by entity (agenda, processo, pessoa, etc.) and by action (create, get, list), while sub-resource tools like easyjur_processo_partes or easyjur_agenda_comentarios have unambiguous scopes. Platform tools (authenticate, connect, marketplace) serve disjoint meta-purposes, so no ambiguity.
Most easyjur_ tools follow a consistent verb_noun pattern (create_agenda, get_processo, list_despesas), but several break it with noun_subresource names (easyjur_agenda_comentarios, easyjur_processo_financeiros) and the platform tools (authenticate, connect, marketplace, report_bug, show_version, toolkit_info) use plain nouns without the prefix. This mixture of conventions makes the set less predictable.
47 tools is well above the threshold for a focused MCP server, even for a comprehensive legal management domain. The inclusion of platform meta-tools inflates the count, and many entities (agenda, processo) have multiple sub-resource readers. This volume risks overwhelming agents and slowing tool selection.
The tool surface provides create, get, and list for each entity, but there are no update or delete operations for any entity. Sub-resources (documentos, partes, mensagens, etc.) are read-only. The only workaround mentioned is creating agenda items to record movements, which is a workaround, not a real update. This is a significant gap that will cause dead ends for workflows requiring modification or removal.