attachments

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

The description discloses that download saves to disk and actions are read-like except download writes to disk, but it doesn't clarify if list/view are safe reads, nor does it mention permissions needed or size limits. Annotations provide readOnlyHint false, which may imply not read-only, but description says actions are non-destructive? Some inconsistency: download writes to disk, which is a side effect, but destructiveHint false. Description doesn't resolve this.

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 brief at two sentences, but the info is densely packed. A more structured format (e.g., listing actions with descriptions) could improve clarity. However, it contains no fluff.

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 description covers the main behaviors (list, view, download), but lacks details on default values, deprecated parameters, and prerequisites (like needing attachmentId for certain actions). Given 5 parameters and no output schema, the description leaves gaps that could confuse an agent.

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?

The input schema already describes all parameters with 100% coverage. The description only recaps the action's three options without adding new semantic details like ID formats or error conditions. It does not compensate for missing parameter constraints beyond 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 explicitly states 'Manage email attachments' and breaks down three actions (list, view, download), clearly distinguishing it from sibling tools like 'read-email' or 'update-email' that handle different aspects.

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 implies usage for attachment management, but does not explicitly contrast with sibling tools or state when not to use it. For instance, there's no guidance on whether 'view' is preferable to 'download' for reading content.

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