get_attachments

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

With no annotations, the description carries the full burden and does disclose the important traits: this writes files to disk, content is never returned inline, and there is a default output directory. It omits other behavior an agent would want — overwrite behavior for existing files, whether the id must be a specific email, and what happens when a keyword matches multiple attachments.

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?

Three tight clauses with the primary behavior and the non-inlining guarantee front-loaded, followed by parameter defaults. No filler; only the lack of visual separation between the two parameter clauses slightly reduces scannability.

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?

An output schema exists, so return values need no explanation, and the description covers the side effect, defaults, and argument forms. The remaining gap is error/edge-case behavior (keyword matching multiple attachments, existing-file overwrite) for a tool that writes to disk.

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 must compensate, and it does for two of three parameters: attachment (blank=all, 1-based index, or filename keyword) and save_dir (blank defaults to ~/Downloads/email-mcp/<account>/). The id parameter is left unexplained, though its meaning is inferable from the sibling tool set.

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 opens with a specific verb+resource: save email attachments to local disk and return a list of paths, plus the key distinguishing note that attachment content is never inlined in the response — which separates it from get_email. It does not name a sibling tool explicitly, so it lands just short of a 5.

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?

It gives clear selection semantics for the attachment argument (blank = all, 1-based index, or filename keyword) and the default save location, which tells an agent how to call it. However, there is no explicit when-to-use/when-not guidance relative to get_email or search_emails, so the routing decision is left implicit.

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