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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile with a low bar. The description adds value by disclosing the return fields (número, série, UF inicial/final, valor do frete, remetente/destinatário, status, datas, status de averbação) and the bulk execution behavior. This is useful context beyond the annotations, especially with no output schema.

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 reasonably efficient (~50 words), front-loads the core purpose and return values, then appends the bulk note. The minor structural issue is the language mixing (Portuguese main body with English bulk sentence), which could cause slight processing inconsistency, but it's not overly verbose.

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 7-parameter tool with no output schema and 0% schema coverage, the description covers return values (compensating for missing output schema), main behavior, and bulk mode. However, it leaves gaps around parameter semantics (account/empresa_id roles, date formats), pagination defaults, and any filtering caveats. It's adequate for selecting the tool but insufficient for fully correct invocation.

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 description coverage is 0%, so the description must compensate. It partially does: 'filtro por data de emissão' implies data_inicial/data_final as a date range, 'paginado' implies pageNumber/pageSize, and 'Bulk support: accepts empresa_ids' clarifies that param. However, 'account' and 'empresa_id' are unexplained, their relationship to 'empresa_ids' is unclear, and no date format or pagination defaults are specified.

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 uses a specific verb ('Lista os CT-e') and resource (Conhecimento de Transporte eletrônico), and specifies scope (da empresa, paginado, com filtro por data de emissão). This clearly distinguishes it from siblings like hivecloud_get_cte (singular fetch), hivecloud_list_mdfes, and hivecloud_list_dces, which target different document types or granularity.

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?

Usage context is implied: it's a paginated list operation with date filtering, and the bulk support note ('accepts empresa_ids for batched execution') gives some guidance. However, there is no explicit when/when-not guidance contrasting with alternatives (e.g., when to use get_cte for a single document vs this list tool), and no mention of default pagination values or authentication prerequisites.

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