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

Beyond the annotations, the description adds valuable behavioral context: labeling is the 'agent's workflow state,' read/unread are mutually exclusive states, and there is no batch form. It does not contradict the readOnlyHint=false or idempotentHint=true 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?

The description is concise and front-loaded: it opens with the action, then provides usage context and constraints. Every sentence earns its place—no filler or redundant restating of the tool name.

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?

Given the rich schema descriptions, annotations, and presence of an output schema, the description covers all essential operational constraints: required labels, one-message limit, and integration with email_list. There are no critical gaps for an agent to call the tool 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?

Schema description coverage is 100%, so the baseline is 3. The description adds extra meaning by explaining the archive label (`archived`), supporting custom tags, and restating the at-least-one constraint. This helps agents understand valid label values beyond parameter names.

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 states a specific verb and resource: 'Add and/or remove labels on one message.' It also clarifies the intended use cases—read/unread, archive, custom tags—and distinguishes the tool from related operations by pointing to email_list's labels.

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?

It gives clear usage context: mark read/unread, archive, apply tags, and filter via email_list. It also states key constraints: supply at least one of addLabels/removeLabels and one message per call. It does not explicitly name alternative sibling tools, but the guidance is clear enough for an agent to know when to invoke it.

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