create_filter

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

The description details criteria and actions, providing some behavioral insight. However, it omits important parameters (account, password) and does not disclose side effects, errors, or authentication needs. With no annotations, the description only partially covers behavioral transparency.

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 structured into criteria and actions, relatively concise with minimal waste. It uses backticks for clarity, though readability could be slightly improved.

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 complexity (21 parameters, no annotations, no output schema), the description lacks return value info, error handling, and authentication context. It is not complete enough for an AI agent to fully understand the tool's usage.

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 0%, so the description compensates by explaining many parameters. It covers most criteria and actions, but misses 'account' and 'password', which are significant. The description adds value beyond the schema but is not complete.

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 creates a filter and lists criteria and actions. It distinguishes from siblings by being the only creation tool for filters, but does not explicitly mention it's for Gmail filters, though Gmail search syntax is referenced.

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?

No guidance on when to use this tool versus alternatives like list_filters or delete_filter. No prerequisites or context for usage are provided.

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