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

Annotations only provide simple flags (readOnlyHint=false, destructiveHint=false), leaving the description to carry the behavioral burden. It does so thoroughly: it discloses that the temporary file copy is deleted after attachment, that the file is compressed and sent by the platform, that file names with more than one dot are rejected, and warns against using file_base64 for conversation attachments. This is far beyond annotations and gives the agent full behavioral expectations.

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 long but information-dense, organized into paragraphs and dash-lists. It front-loads the core purpose and then details the critical usage caveats. While it is not overly verbose, the density requires careful reading; a more structured breakdown (e.g., bulleted parameter usage) could improve scanning, but it remains efficient for the complexity it addresses.

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 complexity (12 parameters, bulk support, no output schema, and nuanced upload workflow), the description is remarkably complete. It covers the two-step upload for conversation/computer attachments, bulk support, constraints, cleanup behavior, and the relationship to sibling tools. Nothing essential for correct invocation is missing.

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 0% schema description coverage, the description must explain all parameters. It does this comprehensively: 'tabela' is explained with examples, 'id' is tied to the specific document table and references 'codigo_lancamento_omie' for payables, and 'arquivo' is explained with the three submission methods including conditions and restrictions. It also covers 'file_name', 'file_path', 'upload_id', and 'upload_ids'. The description adds immense meaning beyond the bare schema.

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 function: attaching a file (receipt, boleto, invoice) to an Omie document, and explicitly names the underlying API operation 'IncluirAnexo'. It also distinguishes itself from siblings by positioning it as the pair to 'omie_lancar/omie_settle_payable', so an agent can immediately know when this tool is relevant.

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 goes beyond a simple 'when to use' by providing detailed guidance: it explains the appropriate context (after launching or settling a payable/receivable), how to handle attachments from conversation or computer (do not read content, call without file, execute upload command, then re-call with upload_id and file_name), and the three ways to supply the file (file_url, upload_id, file_base64) with explicit constraints. This is exemplary usage guidance.

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