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

With annotations present (readOnly=false, destructive=false, idempotent=false, openWorld=false), the bar is higher, yet the description adds substantial behavior: a 30-minute duplicate-suppression window and the duplicado_evitado response field, the requirement that a file_url must open without login, a small-file constraint on base64, and the two-step command-execution upload workflow. None of this is derivable from the schema or annotations.

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?

Front-loaded with the core purpose, then bulleted by parameter and workflow; dense but every line carries operational content, so length is justified for a 7-parameter tool with a multi-step flow. Minor deduction for the trailing English 'Bulk support' sentence that breaks the language register and is terse relative to the rest.

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, so the description must cover enough for correct invocation, and it does: the two-step attachment workflow, dedup behavior, default values, auth-adjacent constraints (URL must open without login), and batch support. An agent has everything needed to call this correctly without opening any sibling.

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 0%, so the description carries the burden, and it does so well: case_id, each attachment mode (file_url/upload_id/file_base64), file_name being required with url/base64, description defaulting to filenames, responsible_id defaulting to the integration user, and permitir_duplicado are all explained, plus a bulk note for case_ids/responsible_ids. Only content_type and upload_code remain undocumented, keeping this just short of a 5.

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 and resource ('Anexa um DOCUMENTO a um processo do Astrea') with concrete examples of document types, and immediately distinguishes itself from the sibling astrea_documento_gerar by clarifying this is attachment, not generation. It further clarifies a scoping subtlety — that the file links to the PROCESSO, never to an andamento/tarefa — which helps an agent route correctly among the many astrea_* siblings.

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 gives explicit selection rules between file_url, upload_id and file_base64, plus a dedicated when-not clause: if the file is a conversation/computer attachment, do NOT read content or build base64, instead call the tool without a file and execute the returned command. The duplication policy (same files within 30 min, use permitir_duplicado=true only on explicit request) is a clean usage condition. Nothing is left to inference.

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