consultar_iaUse para perguntas gerais que não exijam pesquisa web em tempo real. Devolve uma resposta concisa baseada no conhecimento do modelo; não abre URLs nem confirma factos atuais. Para analisar uma página, use analisar_url; para testar critérios com provas, use verificar_condicoes.
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Pergunta ou instrução, entre 1 e 4000 caracteres. Não pressupõe pesquisa web em tempo real. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and does so well: it discloses that the tool returns a concise answer based on model knowledge, does not open URLs, and does not confirm current facts. It does not mention limitations like potential inaccuracy or straightforward refusal for irrelevant prompts, but it covers the critical constraints.
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?
Three compact, scannable sentences with no filler. The primary purpose is front-loaded, followed by clear behavioral notes and sibling references, all earning their 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?
For a simple single-parameter tool with no output schema and no annotations, the description fully covers what the agent needs: purpose, usage limits, behavioral expectations, and routing to alternatives. Nothing essential is missing.
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?
Input schema provides 100% coverage with a clear description of the 'prompt' parameter. The tool description adds only a slight contextual nuance by tying the prompt to general questions but mostly restates what the schema already documents. Baseline of 3 is appropriate.
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?
States a specific verb ('Use para perguntas gerais') and resource scope, immediately clarifying it is a general-knowledge IA tool. It distinguishes itself from siblings by explicitly naming those alternatives, so an agent can tell it apart without inspecting other schemas.
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?
Gives explicit usage context ('perguntas gerais que não exijam pesquisa web em tempo real') and clearly lists which alternative to use for page analysis or criteria verification. This leaves no ambiguity about when to select this tool over its siblings.
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 clearly distinct purpose: analisar_url produces an open-ended page analysis report, verificar_condicoes tests explicit conditions with evidence, and consultar_ia answers general questions without web access. The descriptions also cross-reference one another to remove any confusion.
All three tool names follow the same Portuguese verb_noun pattern in snake_case: analisar_url, consultar_ia, verificar_condicoes. The naming style is consistent and predictable.
With only three tools, the server remains tightly scoped for evidence-backed web verification. Each tool serves a distinct workflow and none feel redundant or arbitrary.
The set covers the main workflows: analyzing a page, verifying conditions against a page, and handling general questions. Minor gaps exist, such as no obvious way to retrieve past verification records or compare multiple pages, but the core purpose is well-supported.