Skip to main content
Glama

validar_citacoes

Validate literal citations against source text before drafting legal documents. Returns verdicts (confirmed, divergent, not found) to flag errors or invented citations.

Instructions

Valida transcrições LITERAIS contra o texto real das páginas — use antes de qualquer relatório/petição. Cada item: {trecho, arquivo, pagina}. Vereditos: CONFIRMADA · QUASE (usa a passagem_real devolvida) · DIVERGENTE (número/data trocado — REJEITAR) · PÁGINA ERRADA (informa onde está de verdade) · NÃO ENCONTRADA (possível invenção — reler a fonte). Só valida citação textual; paráfrase deve ser conferida com obter_pagina.

Input Schema

NameRequiredDescriptionDefault
casoYes
citacoesYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description carries the full burden, and it does substantial work: it enumerates the five verdicts, tells the agent to consume the returned passagem_real on QUASE, to REJEITAR on DIVERGENTE, and warns that NÃO ENCONTRADA may indicate invention. It does not state cost, rate limits, or that the operation is purely read-only, which is the only real gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences, front-loaded with the purpose and the pre-report workflow trigger, followed by the item shape and the verdict taxonomy. No filler or restatement of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values needn't be explained, yet the verdict semantics are still spelled out because they drive the agent's next action. Only the 'caso' parameter's expected format/value is left unspecified, a minor gap for a two-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it does for the critical parameter: the item shape {trecho, arquivo, pagina} is documented nowhere in the schema (citacoes is an untyped array of open objects). The 'caso' parameter is only implicitly identified as the case handle, leaving one gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Valida transcrições LITERAIS contra o texto real das páginas') with an explicit scope limitation (textual citations only, not paraphrases). It also names the sibling obter_pagina as the tool for the out-of-scope case, so an agent can separate it from the other 11 siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit timing ('use antes de qualquer relatório/petição') and an explicit exclusion plus alternative ('Só valida citação textual; paráfrase deve ser conferida com obter_pagina'). Both when-to-use and when-not-to-use are covered.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.