read_attachment

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

The description goes well beyond annotations, explaining that the binary is downloaded to a temporary file, converted, and deleted; that nothing is stored; and that attachment content is untrusted. It also discloses error behavior and the fallback for unsupported formats. This is rich behavioral context that annotations (readOnly, idempotent) do not cover.

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 four sentences, each carrying distinct value: purpose and output, process and side effects, security warning, and error handling. It is front-loaded with the core purpose and contains no redundant or filler text.

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 lacking an output schema, the description explicitly states the return shape ({filename, kind, text}). It covers error conditions, unsupported formats, and data handling, making it complete for an agent to call correctly. There are no missing pieces for a single-attachment read.

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 100%, so the baseline is 3. The description adds no extra parameter-level meaning beyond the schema; it does reiterate that filename must match read_message output and message_id comes from list_messages, but these are already in the schema descriptions. No additional semantics are provided.

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 states a specific verb ('Extract'), resource ('attachment'), and scope ('the TEXT'), and lists supported formats. It clearly distinguishes from sibling tools like read_message, which reads message content, by focusing on attachment text extraction.

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 implies when to use it: whenever an agent needs the text content of an attachment. It doesn't name alternatives because no sibling tool serves the same purpose, and it provides guidance on error and unsupported-format behavior, which helps the agent decide if the tool is appropriate.

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