save_attachment

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

Annotations already declare not read-only, not destructive, not idempotent. The description adds genuinely new context: files are never overwritten and never leave the sandbox, which tells the agent the operation is contained and non-destructive to existing files. This is useful beyond what the annotations provide.

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?

Front-loaded with the core behavior, then a compact Args block. Every line earns its place, though the Args formatting is slightly verbose for the amount of information conveyed.

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?

Complete for a mutation tool: an output schema exists so return values need no explanation, annotations cover the safety profile, and the description covers behavior and all parameters. Missing only explicit guidance on error/ambiguity handling beyond the filename/index hints.

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 carries the full burden, and it delivers: each of the four parameters is explained, including the non-obvious conditional rules for filename ('omit when the message has exactly one') and index ('0-based when filenames are ambiguous'). Minor gap: no format hint for message_id or folder beyond the default.

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+resource ('Save one attachment') plus a clear destination ('local sandbox directory') and scope ('one attachment'). It is easily distinguished from list_attachments and export_email by the save-into-sandbox semantics, though it doesn't name a sibling explicitly.

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?

No explicit when-to-use or when-not-to-use guidance, but the Args section implies the intended workflow (single attachment -> omit filename; ambiguous filenames -> use index). Usage is inferable rather than stated.

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