mark_email_read

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

Annotations only provide destructiveHint=false. The description adds that the tool sets the IMAP Seen flag, which is the core behavioral effect. It does not list any side effects or permissions, but for a simple flag-setting operation, this is adequate and does not contradict annotations.

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 concise sentences. The first sentence defines the purpose and behavior; the second provides usage guidance with an alternative. No wasted words, and key 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 simple tool with two parameters and no output schema, the description covers purpose, usage, and distinguishes from a key sibling. It lacks explicit error conditions or return value info, but these are less critical given the tool's simplicity and the presence of schema details.

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 emailId well, and the description reiterates that. For isRead, the description implies its role ('mark as read or unread') but does not explicitly state that true means read and false means unread, nor does it describe the default. Schema description coverage is 50%, and the description adds marginal value beyond the 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 'Mark a single email as read or unread by setting the IMAP Seen flag.' It uses a specific verb ('mark') and resource ('email'), and distinguishes from batch tools by specifying it handles a single email and can toggle read state.

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?

Explicitly states use case: 'Use for individual triage or to reset read state.' Also provides an alternative: 'Prefer batch_email_action... when updating multiple emails at once.' This helps the agent decide when to use this tool versus siblings.

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