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

Goes beyond annotations by disclosing implicit side effects: labels are created on first use, adding 'trash' hides the message from reads and searches, and removing it restores the message. That reversibility detail supports the destructiveHint=false annotation and tells the agent the operation is recoverable, though response/error behavior is unstated.

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 dense sentences with the core action front-loaded and the special-label semantics following. No filler, every clause carries 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?

For a 4-param mutation with low schema coverage and no output schema, it covers limits, label creation semantics, and the trash/unread special cases well. It lacks detail on combining add and remove in one call and on failure modes, but is largely sufficient for correct invocation.

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 only 25% (only mailbox is documented), so the description must compensate. It does add meaning for the label params ('plain names, created on first use') and clarifies the messageIds cap ('up to 50 messages'), but does not explain the addLabels vs removeLabels distinction or that they are separate arrays.

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?

States specific verbs (add/remove) plus resource (labels on AgentMail messages) and scope (up to 50 messages). An agent can immediately tell this is the AgentMail labeling tool and not the Gmail equivalent or a folder/move tool.

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?

Explains the practical scenarios for special labels ('Add trash to move a message to trash... remove unread to mark it read'), which tells the agent when to reach for those values. It does not name or compare against alternatives like apply_gmail_labels or move_messages, so it stops short of explicit when-not guidance.

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