save_attachment

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

With no annotations, the description carries the full behavioral burden, and it does disclose a real side effect plus ordering: the destination directory is created recursively before Mail is contacted, meaning a filesystem write can occur even if the mail operation fails. It omits equally important behavior for a disk-write tool: whether an existing file of the same name is overwritten, and what the tool returns (e.g., the resolved path).

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?

Two short sentences, both front-loaded: the action first, then the side-effect ordering. Nothing is padded or repeated from the schema.

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 five-parameter tool with full schema coverage, no output schema, and no annotations, the description supplies the one non-obvious behavioral fact (recursive directory creation before the Mail call). Remaining gaps around overwrite behavior are secondary for an agent that just needs 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 100%, so all five parameters, including the savePath default of ~/Downloads, are already documented in the schema. The description adds no new meaning about path semantics, filename collisions, or how attachmentName is matched, so the baseline 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?

"Save a specific attachment from a message to disk" gives a concrete verb (save), a concrete resource (attachment), and a destination (disk). The word "specific" implicitly separates it from the sibling save_all_attachments, but that sibling is never named, so the differentiation is inferential rather than explicit.

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 implied rather than stated: the agent can infer this tool is for one attachment while save_all_attachments handles bulk, but no sentence says when to pick one over the other. There is also no guidance on prerequisites, such as whether the attachment must first be listed via list_attachments.

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