Mark Email Read/Unread

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

Annotations already indicate the tool is not read-only, non-destructive, and idempotent. The description adds value by warning about silent no-ops when sourceFolder is omitted: 'IMAP UIDs are folder-scoped and silent no-ops can otherwise occur.' This explains a subtle behavioral trait beyond annotations. However, it does not detail the exact mutation (e.g., whether it sets flags only) or any rate limits.

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 sentences with no fluff. The first sentence states the primary action and defaults. The second sentence provides the critical usage guideline. Every sentence earns its place, and the information is front-loaded.

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 3-parameter tool with an output schema, the description covers the essential purpose, a key gotcha (folder scoping), and a default. The output schema presumably documents the return value. With the annotations providing safety info, the description is complete enough for an agent to use 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?

The input schema covers 3 parameters with only sourceFolder described in detail (33% coverage). The description adds default for isRead ('isRead defaults to true') and repeats/emphasizes the important sourceFolder admonition. For emailId, no extra meaning is provided beyond the schema's basic type. While it partially compensates for low schema coverage, a description of emailId's format (e.g., numeric UID) would strengthen it.

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 purpose: 'Set the read/unread status of an email.' It specifies the verb ('set'), the resource ('email'), and the property ('read/unread status'). It also distinguishes itself from siblings like bulk_mark_read by focusing on a single email and providing critical details about folder scoping.

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 explicit guidance on when to use the sourceFolder parameter: 'Pass sourceFolder whenever the UID came from a folder other than INBOX.' It also warns against using 'All Mail' as a source. However, it does not compare this tool to alternatives like bulk_mark_read or mark_answered, leaving the agent to infer when to use each. A clear when-not-to-use statement would elevate the score.

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