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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the bar is lower. The description adds genuinely useful context beyond annotations: the returned artifacts and, importantly, that download_url is a 1-hour presigned URL, which signals expiry behavior an agent must plan around.

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?

Tight and front-loaded: a purpose sentence, a labeled 'When to use' list, and a compact 'Returns' line. No filler, and every clause carries operational information.

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?

Although there is no output schema, the description enumerates the exact return fields (filename, mime_type, byte_size, download_url), covering the gap. Combined with the workflow trigger and full schema coverage, an agent has everything needed to invoke and consume it.

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 both file_ids (max 20) and the in_workspace override are fully documented in the schema, including the 'nothing is stored' semantics. The description adds no parameter-level guidance, so the baseline of 3 applies.

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 (get) and resource (metadata and download URLs for files) with the key scoping detail 'by their IDs'. This cleanly separates it from siblings like files_get_base64, files_read, and files_ingest, which handle content rather than metadata/URLs.

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?

Provides explicit when-to-use triggers, notably 'after messages_read_history returns attachment_file_ids' and 'to get a presigned download URL to read a received file'. It does not, however, state when NOT to use it or point to alternatives like files_get_base64 or files_read for actually reading content.

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