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

Annotations already indicate read-only, idempotent, non-destructive, which the description reinforces by stating it lists (read operation). The description adds behavioral details: pagination, listing of specific fields, and tenant id requirement on the connection, which go beyond the annotations. No contradiction is present.

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 extremely concise, containing only two sentences. The first sentence states the main purpose and output fields; the second adds a critical prerequisite and bulk capability. No extraneous information or filler. Every sentence is purposeful, achieving high clarity without verbosity.

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?

Despite simple annotations, the tool has 7 parameters with no schema coverage and no output schema. The description does not provide enough information for the agent to understand all input semantics (e.g., pageSize, data_inicial, data_final), the pagination mechanics, or the shape of the response. It lists some output fields but not how to control pagination or filter by dates/company. This is inadequate for operational use.

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 explain all 7 parameters. It only mentions `empresa_ids` for bulk support and implies pagination (pageSize, pageNumber, data_inicio/fim) but does not describe each parameter's meaning, format, or purpose. This critical gap severely reduces an agent's ability to correctly invoke the tool.

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 it lists MDF-e (Manifesto Eletrônico de Documentos Fiscais) of the company with pagination, and specific fields (number, series, emission date, status, loading/unloading UF, CIOT). It distinguishes itself from sibling tools like hivecloud_list_ctes or hivecloud_list_dces by explicitly naming MDF-e. The verb 'List' and resource 'MDF-e' are specific and unambiguous.

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?

It provides essential context: requires mdfe_tenant_id on the connection, which is distinct from CT-e, and accepts empresa_ids for batched execution. However, it does not explicitly say 'use this instead of X' or mention when not to use it. The context implies usage only for MDF-e, but excludes mention of alternatives beyond noting the distinct tenant requirement.

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