Retorna apenas a timeline de movimentações (+ metadados) de um processo — ideal pra detectar se houve movimentação nova. Sem resultado, instancias vem vazio acompanhado do mesmo bloco ausencia de datajud_get_processo (motivo provável + explicação) — leia antes de re-tentar.
| Name | Required | Description | Default |
|---|---|---|---|
| tribunal | Yes | ||
| numero_processo | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already signal readOnly, idempotent, non-destructive. The description adds valuable behavior beyound that: it explains the no-result shape (`instancias` vazio with an `ausencia` block), and warns the agent to read that block before retrying. This is genuinely useful behavioral disclosure.
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?
Two sentences carry high signal density: the first front-loads purpose and use case, the second handles the edge case and retry guidance. There is no filler or redundancy.
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 description covers the empty-result case well and points to a sibling for the `ausencia` explanation, which is helpful. However, with no output schema, the description does not fully describe the normal return structure of `movimentacoes` and its metadata fields. It is adequate for a simple timeline check, but not complete.
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 explain the parameters or their formats. While `tribunal` is constrained by an enum and `numero_processo` is self-descriptive as a case number, the description provides no additional meaning about expected input formats or how they relate to the returned timeline.
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 ('Retorna') and a specific resource ('a timeline de movimentacões (+ metadados) de um processo'), clearly distinguishing it from a full case fetch by saying 'apenas'. It also ties it to a concrete use case, detecting new movements, which makes its purpose unmistakable.
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 gives clear usage context: use this when you need to detect whether a case has new movements. It does not explicitly list alternatives or when-not instructions, but it does reference datajud_get_processo for the empty-result block, which indirectly orients the agent toward related tools.
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 has a distinct purpose with clear descriptions. The DataJud-specific tools (datajud_*) are well-separated from platform tools (authenticate, connect, marketplace, etc.), and even similar tools like datajud_get_processo and datajud_movimentos are differentiated by their scope.
Naming conventions are inconsistent: some tools are plain verbs (authenticate, connect), others are nouns (marketplace, toolkit_info), and the datajud_ prefix is applied to a mix of noun and verb phrases (datajud_movimentos vs datajud_get_processo). This lacks a predictable pattern.
With 10 tools, the count is within the typical range for a server. However, the inclusion of generic platform tools alongside domain-specific DataJud tools slightly dilutes the focus, though each tool serves a distinct role.
The DataJud domain coverage is adequate for common operations (login, search, fetch details, movements, raw query). The platform tools also cover essential actions like marketplace management and bug reporting. Minor gaps exist (e.g., no tool for listing available courts), but overall it's functional.