attachments

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

The description accurately notes that list is read-only, while view and download have side effects (inline content retrieval and file saving). It mentions auto-creation of outputDir and deprecation of savePath. Annotations indicate readOnlyHint=false and destructiveHint=false, and the description aligns with that. No contradictions. Could be improved by stating permission requirements or rate limits, but currently adequate.

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 a single paragraph that is well-structured and front-loaded with the primary purpose. Every sentence adds distinct information without redundancy. It efficiently covers all actions, parameters, and return values.

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?

Despite lacking an output schema, the description fully explains return values for each action: list returns metadata fields, view returns inline content, download returns a file path. All essential aspects (actions, required parameters, special behavior for binary types, deprecation) are covered. The description is complete for a tool of this 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?

Schema coverage is 100%, providing baseline for 3. The description adds significant value beyond the schema: explains the purpose of each action enum value, clarifies default behavior, notes deprecation of savePath, and outlines the behavior of outputDir (auto-created, defaults to tmpdir). This compensates well for the already complete schema.

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 'Inspect or retrieve email attachments' and enumerates the three actions (list, view, download) with specific behaviors. It effectively distinguishes this tool from siblings like read-email or export by focusing on attachment operations.

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 provides clear guidance on when to use each action (list for metadata, view for inline content of text/JSON/XML, download for binary attachments) and specifies required parameters per action. While it doesn't explicitly state when not to use this tool versus alternatives, the context is sufficient for an AI agent to make appropriate decisions.

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