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

Annotations already cover readOnly, idempotent and openWorld, so the bar is lower, and the description adds real behavioral context beyond them: the 200-with-fresh-URL vs 202-while-processing contract and the card-index error case. It stops short of saying whether the URL expires or requires authentication to fetch.

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?

Very short and front-loaded, with status semantics stated immediately. The only waste is restating the title 'Get attachment' as the opening line, which duplicates the title field.

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?

With no output schema, the description does explain the response status contract, which is the most important thing an agent needs. However, it leaves the parameter meanings and the shape/lifetime of the returned URL unspecified for a two-required-parameter tool.

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 0% and neither parameter is documented in the schema. The description only obliquely clarifies 'index' by describing the card-index failure mode; messageId is never explained, so the description does not compensate for the coverage gap.

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 ('Get attachment') and the payload is clarified as a URL-bearing media fetch. It does not need to distinguish itself from siblings since no other attachment tool exists, but it also never states explicitly that it returns a media URL for one attachment of a message.

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?

Usage is only implied. The 202 case tells the agent that polling/retrying is expected while media is pending, and the invalidRequest note tells it not to call with a card index, but there is no explicit when-to-use guidance or pointer to alternatives such as messages_get for metadata.

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