gmail_search_emails

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

Annotations already declare readOnlyHint, destructiveHint=false, idempotentHint. The description adds useful behavioral context beyond annotations: it returns compact summaries, supports pagination via page_token, and excludes full bodies. This clarifies the read-only scope and return shape. It does not contradict 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?

Two sentences, front-loaded with the core purpose and return payload. Every word earns its place; no fluff or repetition. Ideal size for a tool of this complexity.

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?

The tool has 4 parameters and an output schema. The description covers the essential behavior: search, return summaries, pagination, and read-only nature. It does not explain pagination looping or error handling, but the schema and annotations fill gaps. Overall complete enough for an agent to invoke 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 0%, so the description should compensate for parameter details. It only mentions Gmail search syntax for 'query' and pagination for 'page_token', adding some context. However, it does not explain 'tags' or 'max_results' beyond what the schema already provides. Since the schema itself has thorough descriptions, the addition is minimal but not harmful.

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 uses a specific verb ('Search Gmail') and resource, and clearly states what it returns (compact message summaries with listed fields). It distinguishes from sibling gmail_search_email_ids by noting it returns summaries, not just IDs, and from thread-reading tools by explicitly saying it does not return full bodies.

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 states to use Gmail search syntax and mentions pagination, giving clear operational context. The 'does not return full bodies' implies using a different tool for full content, but it does not explicitly name alternatives like gmail_read_email_thread or gmail_batch_read_email. This is clear but not fully explicit.

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