read_attachment

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

No annotations are provided, so the description bears full burden. It clearly discloses behavior: metadata always returned, base64 content if under size limit, warning for large ones, link for URL-type, and include_data option to skip data fetch. No contradictions.

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 moderately detailed with a summary line, then detailed conditions and parameter docs. Every sentence adds value, though slightly verbose; could be tightened.

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 presence of an output schema (so return values not needed), two parameters clearly explained, and full behavioral coverage, the description is complete for an agent to invoke correctly.

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%, requiring description to compensate. The description explains both parameters: attachment_id as the id, and include_data as a boolean to control base64 fetch, adding meaning far beyond the schema's type and default.

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 reads an ir.attachment, specifying that metadata is always returned and base64 content is included when the attachment is small enough. This distinguishes it from sibling tools like read_records which read generic records, and none of the other siblings handle attachments specifically.

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 explains when to use the tool (reading attachments), provides conditions for different attachment types (binary vs URL) and size thresholds, and clarifies the include_data parameter. It does not explicitly state when NOT to use it or mention alternatives, but the context is clear.

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