Catálogo Blucher

Bibliografia Blucher para uma ementa

recomendar_para_ementa

Read-onlyIdempotent

Dada a ementa (programa) de uma disciplina, aponta quais livros e capítulos da Blucher cobrem cada tópico, quais livros formam o núcleo da bibliografia e quais tópicos ficaram sem cobertura. Use quando um professor, coordenador ou aluno colar uma ementa ou lista de tópicos e quiser bibliografia. Aceita texto livre, lista ou tópicos numerados. A ementa não precisa de nome, e-mail ou telefone do professor. Cada livro traz url, o link da página dele.

Given a course syllabus, maps each topic to Blucher books and chapters, lists the core books and the topics with no coverage. Use it when a teacher or student pastes a syllabus or topic list and wants a reading list. No personal data is needed. Each book carries url, the link to its page.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "ementa": "<ementa>"
    },
    "name": "recomendar_para_ementa"
  }
}

Input Schema

Name	Required	Description
`nivel`	No	graduacao \| pos \| profissional (ainda sem efeito: o nível dos livros está sendo cadastrado). / Level (no effect yet).
`ementa`	Yes	Texto da ementa: livre, em lista ou numerado (20–8.000 caracteres). / Syllabus text.
`max_por_topico`	No	Sugestões por tópico (1–5). / Suggestions per topic.

Output Schema

Name	Required	Description	Default
`aviso`	No
`nucleo`	No
`topicos`	Yes
`observacao`	Yes
`sem_cobertura`	No
`complementares`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 27, 2026

addedOutput schema / $defs / LivroCobertura / properties / url / description

Added value: +"Página do livro em www.blucher.com.br: o link do livro. / The book's page on www.blucher.com.br."

addedOutput schema / $defs / Sugestao / properties / url / description

Added value: +"Página do livro em www.blucher.com.br: o link do livro. / The book's page on www.blucher.com.br."

First observedOct 26, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real value: accepted input shapes (free text, list, numbered topics), no personal data needed, and that each book carries a `url` to its page. It stops short of describing ordering, scoring, or how coverage gaps are determined.

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

Conciseness3/5

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

The content is well front-loaded and the core mapping is stated in the first sentence. However, the full text is duplicated in Portuguese and English, roughly doubling length without adding information — justified for bilingual users but a real cost against conciseness.

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?

With an output schema present, the description needn't detail return values, and it still summarizes them (topic mapping, core books, uncovered topics, per-book url). Input formats and privacy expectations are covered. What's missing is guidance on limitations, such as behavior when a syllabus has zero matches or how topics are segmented.

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 coverage is 100%, so baseline is 3. The description earns above baseline by clarifying the `ementa` parameter's accepted formats (free text, list, numbered topics) and by noting it needs no professor name/email/phone. The `nivel` and `max_por_topico` parameters are left entirely to the schema, which is acceptable given full coverage.

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 transformation: given a syllabus, it maps each topic to Blucher books and chapters, identifies core books, and flags topics with no coverage. That is clearly distinct from a keyword search like buscar_livros, so an agent can route between them without opening a schema.

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

Usage Guidelines4/5

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

Explicit trigger context: use when a teacher, coordinator, or student pastes a syllabus or topic list and wants a reading list. It also states that no personal data is required, which preempts a common hesitation. It does not, however, name sibling alternatives (e.g., buscar_livros for single-book lookup) or state when not to use it.

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

All Catálogo Blucher tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?