Mail Search

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

With no annotations, the description carries the full burden and does so well: it discloses limit semantics (default 50, hard max 200, over-max clamped not rejected, <= 0 rejected) and how folderPath resolves from the default mail store's root. It stops short of full transparency — result ordering, error behavior for a nonexistent folderPath, and explicit read-only/auth status are unstated.

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 front-loaded: the core purpose leads, and every clause about folders, filters, and limit earns its place with zero filler. The heavy parentheticals and em-dash chains make it harder to scan than a structured list, but nothing is redundant or 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?

Given 7 nullable parameters with interdependent constraints and an output schema that documents return values, the description gives an agent everything needed for a correct first call: the XOR folder rule, the at-least-one filter rule, and clamping semantics. Remaining gaps — invalid-folderPath error behavior and result ordering — are minor for successful 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 description coverage is 0%, so the description must compensate — and it covers every parameter: folder vs folderPath mutual-exclusivity semantics, '/' delimited path meaning, substring semantics for subject/sender, date-range meaning for dateFrom/dateTo, and the limit clamp/reject behavior. This vastly exceeds what the bare schema provides.

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 'Search the default Outlook Inbox, Sent Items, or Drafts folder' — a specific verb (Search), a concrete resource (Outlook mail folders), and a defined scope (folder/folderPath selection plus filters). This clearly distinguishes it from sibling search tools targeting calendar, tasks, files, and OneNote, and from mail_get_message by the search-vs-fetch semantics.

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 gives clear invocation context: 'exactly one of folder/folderPath is required' and 'at least one of dateFrom/dateTo/subject/sender is required,' which tells an agent precisely when the tool is appropriate and what it needs. However, it never names a sibling alternative (e.g., mail_get_message for single-message retrieval), so there is no explicit when-not or exclusion guidance.

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