gmail_search_messages

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

With no annotations, the description carries the full burden for behavioral transparency. It implies a read operation (search) but does not explicitly state that it does not modify data, nor does it mention rate limits, authentication needs, or error behavior. The output schema exists but is not described; however, per the rules, output schema reduces the need to explain return values. The description provides basic behavioral context but lacks depth.

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 a single, concise sentence (14 words). It is front-loaded with the primary action and includes examples efficiently. Every word contributes to understanding the tool's purpose, with no fluff or redundancy.

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 tool has low complexity (2 params), no annotations, and an output schema (reducing need to describe returns), the description is adequate but incomplete. It explains the query parameter well but omits guidance on max_results, pagination, or rate limits. The sibling tools context highlights the need for clearer differentiation, which is only partially addressed.

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 must add meaning beyond parameter names. It does explain the 'query' parameter by describing Gmail search syntax and giving examples. However, it completely ignores the 'max_results' parameter, even though its default value (10) is specified in the schema. The description adds partial value for one parameter but fails to cover all parameters adequately.

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 searches Gmail using Gmail search syntax, with examples like from:, subject:, is:unread. This distinguishes it from sibling tools like gmail_list_messages (which likely lists messages without search capabilities) and other Gmail tools. However, it does not explicitly contrast with other search or list tools, so the differentiation is implied rather than explicit.

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 provides how to use the tool (with Gmail search syntax) but gives no guidance on when to use it versus alternatives (e.g., when to use search vs. list vs. read). It lacks explicit exclusions or context about prerequisites or limitations. The examples help, but the usage context is not fully elaborated.

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