read_attachment

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

No annotations exist, so the description carries full burden. It discloses a key behavioral trait: the binary is never passed to the agent, and only text extraction occurs for the listed formats. It does not discuss error behavior or permissions, but for a read-only tool this is a reasonable level of disclosure.

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 two concise sentences, front-loaded with the purpose and supported formats, with no redundant filler. Every sentence earns its place.

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 annotation or output schema, and the description omits parameter semantics and return format details. It covers the main purpose and binary behavior but leaves gaps around optional parameters and expected output structure.

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?

The schema has 4 parameters with 0% description coverage, and the description does not clarify the role of folder/account_id or the relationship between message_id and filename beyond obvious naming. It adds little beyond the schema, failing to compensate for the missing parameter descriptions.

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 ('Estrae il TESTO') and resource ('un allegato'), lists supported formats (pdf/docx/xlsx/txt), and clearly distinguishes itself from sibling tools like read_message and read_knowledge_file. The binary-not-passed note further clarifies scope.

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 usage context is implied (use when you need attachment text), but the description offers no explicit when/when-not guidance or alternative tool names. It does not mention that read_message should be used for message body content instead.

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