search_emails

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

With no annotations, the description carries the full burden of behavioral disclosure. It adds valuable behavioral facts beyond the basic purpose: results are metadata-only, body is empty, and results are returned in server order rather than sorted. It does not mention pagination or limit behavior, but the core behavior is transparent enough.

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 compact and front-loaded, starting with the search criteria, then result behavior, then the routing note. Every clause adds distinct value and there is no filler.

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 description covers main search semantics and returns metadata, and the output schema exists to document return fields. However, with 0% parameter schema coverage and no annotations, the absence of folder semantics and date/query format details leaves meaningful gaps for an agent trying to invoke the tool 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 must compensate for parameter meaning. It maps query, sender, and date range to the likely parameters (query, from_email, since/until), but it does not explain the folder parameter, date string format, or query syntax. Partial compensation only.

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 by keyword, sender, and date range, with a specific verb and resource. It also explicitly distinguishes itself from read_email by noting that results contain metadata only and the body is empty.

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 gives an explicit when-not-to-use condition: if you need the email body, use read_email instead. This is a clear alternative and exclusion, making the usage boundary unambiguous.

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