Pesquisar fontes na web

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

Goes beyond the annotations by disclosing latency characteristics (~30 s quick mode vs several minutes for Deep Research), the possibility that results are not ready when the call returns, and that importing mutates the notebook's source list. It does not mention quota/credit implications or limits on how many results can be imported, which would matter for a costly open-world operation.

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?

Dense but well ordered: capability first, then the with/without 'consulta' distinction, then import options and defaults. Some phrasing is packed into a single long sentence, but nothing is redundant.

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?

There is no output schema, yet the description conveys what the agent gets back (a numbered list of results, or imported sources) and how to act on it. Missing is any statement of how results are presented when only listing, or what happens to previously imported sources.

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 coverage is 100%, so the baseline is 3; the description earns above that by explaining the conditional default for 'importar' (all for a new search, none when called without a query) and by giving a concrete example format ([1, 3]) for numeric selection. It does not clarify whether indices refer to positions in the listed output or an internal ranking.

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+resource ('Usa a pesquisa de fontes do NotebookLM ... e importa os resultados como fontes') and distinguishes itself implicitly from notebook_adicionar_fonte / notebook_fontes by covering web search rather than manual source addition. An agent can identify this as the search-and-import tool without opening the schema.

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?

Explicitly splits the two invocation modes: with 'consulta' it runs a search, without it lists/imports results from the last search, and it explains why (research outlasting the call). It also states the default import behavior for each mode, which is exactly the decision an agent has to make.

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