gmail_discover

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

Beyond the readOnlyHint annotation, the description discloses a key behavioral trait: 'Operational gmail tools are hidden until discovered.' This explains why this tool must be called first and sets expectations for how the tool system works. No contradiction with 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 front-loaded with purpose and usage in the first two sentences, then provides a comprehensive list of operations. While the list is very long, it is necessary and directly supports the tool's purpose. It is structured but could be seen as verbose due to the exhaustive enumeration.

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?

With no output schema, the description compensates by listing all available operations, giving the agent a clear expectation of the return content. It also explains the discovery mechanism and ordering. Slightly more detail on the return format (e.g., list vs. table) would make it complete, but the essential information is present.

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 schema already describes the 'query' parameter with 100% coverage ('Keyword to filter the returned operations'). The description does not add any additional meaning to the parameter itself, but it does list the operations that would be returned, which adds context to the tool's output rather than the input. Baseline 3 is appropriate.

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 opens with a specific verb and resource: 'List the available gmail operations.' This clearly distinguishes it from sibling discover tools (e.g., drive_discover, calendar_discover) which target other services. The explicit operation list further confirms the scope.

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 explicitly instructs 'call this first, then call the tool you need by name.' This tells the agent exactly when to use it and implies that other gmail tools should be called after discovery. The sibling discover tools provide obvious alternatives for non-Gmail services.

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