search_emails

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

No annotations exist, so the description carries the burden. It adds useful non-obvious behavior: UIDs are permanent and do not change when emails are deleted, which helps agents trust them for future calls. It does not explicitly state read-only status, though 'Search' implies it.

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?

Three sentences, all contributing value: the purpose is front-loaded, the UID permanence note is meaningful, and the chaining guidance is actionable. No filler 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?

With no output schema, the description adequately explains the return value (UIDs) and how to use it. It covers the important chaining behavior and leaves parameter specifics to the highly detailed schema, making it sufficiently complete for correct invocation.

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 100% with detailed parameter descriptions, so the baseline is 3. The description adds no parameter-level meaning beyond the generic 'advanced filters' phrase, which does not enhance the schema.

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 emails with advanced filters and returns UIDs, which are stable identifiers. It distinguishes itself via the focus on UIDs for downstream operations, but does not explicitly contrast with sibling tools like list_emails, and the phrase 'using UIDs' is slightly awkward.

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 tells agents to use this tool when they need UIDs for subsequent operations, providing a clear context. It does not explicitly state when to prefer list_emails or exclude alternatives, so it stops short of a 5.

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