send_message

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

While the description reveals that send_message sends immediately and sets threading headers for replies, it lacks details on side effects, rate limits, authentication requirements, or undo capabilities. With no annotations, more behavioral disclosure would be beneficial.

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 sentences pack essential information without fluff. The most critical guidance (prefer create_draft) is front-loaded. Every sentence earns its place.

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 7 parameters and no output schema, the description adequately covers the tool's purpose, usage guidelines, key parameter semantics, and multi-account behavior. It is sufficient for an AI agent to understand when and why to use it, though it could mention error handling or return values.

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 71%, and the description adds value beyond the schema by explaining that replyToMessageId sets threading headers and threadId automatically, and that subject and to are optional when replying. It also clarifies the account parameter's usage.

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 it sends an email immediately, specifies it works with multi-account Gmail, and distinguishes from create_draft by advising to prefer draft unless user explicitly approves sending. It also mentions support for replies via replyToMessageId.

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?

Explicitly advises to prefer create_draft unless user has explicitly approved sending, providing clear guidance on when to use this tool. Also notes that replies are supported via replyToMessageId, indicating appropriate scenarios.

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