download_attachment

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

The description discloses two valuable behaviors: base64 output encoding and a 5 MB hard cap, which is genuinely useful context. However, with zero annotations the description carries the full burden, and it fails to say what happens at the cap (error vs truncation) or for a missing attachment — exactly the behavioral detail an agent needs for error handling.

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?

A single, front-loaded sentence where the verb and resource lead, with the encoding format and size limit following as compact parenthetical context. Every word earns its place with zero filler.

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?

For a tool with 4 parameters, no annotations, and 0% parameter documentation, the description is too thin. The output schema covers return structure, but required parameter semantics and cap-failure behavior remain undocumented, leaving an agent with real uncertainty about how to invoke the tool 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 description coverage is 0%, so the description needed to compensate but does not. Neither required parameter is explained: uid is ambiguous (email UID vs attachment ID) and the relationship between uid and filename as the attachment selector is left to guesswork. Parameter names and defaults carry the only meaning, which is insufficient at 0% coverage.

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 ('Download'), a singular resource ('one attachment'), and a format detail (base64), making the tool's job unmistakable. This cleanly separates it from all email- and mailbox-level siblings like get_email or list_emails, since no other sibling handles attachment content.

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 use case is implied — call this when you need an attachment's raw content, likely after fetching an email — but nothing explicitly states when to prefer it over get_email or that uid/filename must first be obtained from an email fetch. There is no exclusion guidance or prerequisite statement.

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