create_filter

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

With no annotations provided, the description carries the full behavioral burden and does so well: it discloses that filters only affect mail arriving after creation, that labels must already exist, that at least one criterion and action are required, and that off-account forwarding is impossible. It could add error behavior or idempotency details, but the essential side effects and limitations are clearly communicated.

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 dense but well-organized: purpose and differentiation first, then parameter constraints and actionable categories, then critical caveats. Every sentence contributes unique information, and there is no redundant restating of schema field names.

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 tool with 12 parameters, no annotations, and no output schema, the description covers the required decision points: which parameters are match criteria, which are actions, the minimum combination rule, the label existence requirement, the future-only behavior, and how to handle existing backlog. The agent has enough context to invoke the tool correctly and to route related tasks to modify_labels or search.

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 100%, so the baseline is 3, but the description adds meaningful grouping beyond the schema: it separates match criteria from actions, defines the convenience flags (archive/mark_read/delete/star), and explains that add_labels/remove_labels accept names or ids. This helps an agent select and combine parameters correctly without needing to infer relationships from the flat 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 the verb 'Create a Gmail filter' and the resource, and immediately differentiates it from modify_labels by noting this is the 'durable fix' for recurring noise versus touching only existing messages. This makes the tool's purpose unmistakable even among many siblings.

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 explicitly names the alternative tool modify_labels, explains when it is the wrong choice ('only touches existing messages'), and even instructs the agent to 'clear existing backlog with search + modify_labels.' It also states that filters cannot forward mail off-account, removing a potential misapplication.

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