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

Beyond the annotations, the description adds substantial behavioral detail: it creates a draft, stays in 'digitação' for review, does not transmit, requires allow_writes, and uses the last authorized CT-e as a base. It also explains that it fills load, values, and parties, and describes bulk execution semantics.

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?

The description is compact and well-structured: the first sentence states the purpose, the second explains the data import and defaults, the third clarifies the non-transmission behavior, and the fourth gives the prerequisite and bulk capability. Every sentence adds value with no filler.

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?

Given the tool's complexity (13 params, no output schema), the description provides a solid overview of behavior, state, prerequisites, and bulk support. It doesn't explain what the function returns (e.g., draft ID) or distinguish singular vs. plural parameters like template_cte_id vs. template_cte_ids, which keeps it from a 5.

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?

With schema_description_coverage at 0%, the description must compensate, and it partially does by naming nfe_chaves, template_cte_ids, and empresa_ids, and explaining that values are auto-filled from the NF-e and last CT-e. However, many parameters (tomador, cfop_codigo, cfop_natureza, responsavel_frete, produto_predominante, observacao, account, etc.) remain unexplained, leaving a significant gap.

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 clearly states the tool's specific function: 'Cria um RASCUNHO de CT-e a partir de uma ou mais chaves de NF-e' — creates a draft CT-e from NF-e keys. It explicitly notes that it does NOT transmit to SEFAZ, distinguishing it from siblings like hivecloud_cte_emitir.

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 context: use this to create a draft for review, not to transmit. It also states a prerequisite ('Exige allow_writes na conexão') and mentions bulk support. However, it doesn't explicitly name an alternative such as 'use hivecloud_cte_emitir to transmit,' so it falls just short of a 5.

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