download_attachment

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

Annotations provide readOnlyHint=false, destructiveHint=false, etc. The description adds value by disclosing that the tool can either return a URL or save to disk depending on savePath. This behavioral nuance is beyond what annotations convey. No contradictions found.

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?

The description is two sentences: one stating the core function and one providing usage guidance. It is front-loaded, every sentence adds value, and there is no redundant or extraneous 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?

The tool has no output schema, so the description could have described the return value (e.g., a download URL). However, the context of sibling tools and annotations provides sufficient background. The description is adequate for the tool's complexity.

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?

Input schema has 100% description coverage for all three parameters. The description adds conditional meaning: 'when savePath is provided' triggers save-to-disk behavior, otherwise returns URL. This clarifies the parameter's role beyond the schema's description.

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 clearly states the tool's function: 'Get an attachment download URL or save an attachment to disk when savePath is provided.' It specifies the verb (get/save) and resource (attachment), and distinguishes from siblings like get_email_attachments by noting its use case.

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 description explicitly tells when to use the tool ('when the user wants the file from a specific message attachment') and provides a clear negative case with an alternative: 'Do not use when you still need to discover attachment IDs; use get_email_attachments first.'

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