search-emails

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

Beyond the readOnlyHint annotation, the description discloses important behavioral nuances: automatic fallback through OData filters / boolean filters / recent listing on Outlook.com, deprecated alias behavior for kqlQuery, auto-quoting of search tokens, and the mechanics of delta tokens for incremental sync. This adds significant value beyond the 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?

The description is dense but well-organized, front-loading the core purpose and then systematically explaining each mode. It is long, but given 21 parameters and multiple modes, every sentence contributes necessary information without fluff. A tighter structure with bullet points could improve readability, but no sentence is wasted.

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 return values ("Returns paged messages with id/subject/from/receivedDateTime/preview by default"), mode behavior, personal account limitations, and parameter interactions. With no output schema, this is sufficient context for an agent to select and invoke the tool correctly across all its modes.

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?

While the input schema already covers all 21 parameters with descriptions, the tool description explains how parameters interact to select modes (e.g., deltaMode with deltaToken, searchExpression bypassing other params, groupByConversation vs conversationId). This cross-parameter semantic guidance goes beyond what the schema provides, though the baseline is 3 due to high schema coverage.

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 opens with a clear verb+resource statement: "Search, list, delta-sync, or thread-group emails — six modes selected by parameters (read-only)." It enumerates the distinct modes and explicitly notes the tool is read-only, which distinguishes it from sibling mutation tools like send-email and update-email.

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 detailed guidance on when to use each mode, such as "ideal for inbox monitoring" for delta mode and explicit fallback behavior on personal Outlook.com accounts. It does not explicitly contrast with direct alternatives like read-email for single-message lookup, but the mode distinctions and parameter guidance adequately convey usage context.

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