Mail

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

Annotations already declare readOnly/idempotent/non-destructive, so safety is covered. The description adds useful behavioral detail beyond that: preview text vs. full body return shape, and which parameter combination triggers which mode. It does not mention pagination, volume caps, or auth prerequisites.

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?

A single dense paragraph with the core action front-loaded and mode behaviors following. Every clause maps to a real parameter; no filler. Slightly packed but readable.

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?

For a read-only, open-world list/drill-down tool with no output schema, the description plus the fully documented schema covers the modes an agent needs to select and call correctly. Missing only edge behavior like pagination or result limits, which are minor here.

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 100%, so the schema already documents all 7 parameters including the folder default and the filter shortcuts. The description restates the same mode mappings rather than adding syntax or interaction rules beyond what the schema provides, so the baseline 3 applies.

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 states a specific verb and resource ('Read the user's recent emails from Microsoft 365') and separates the two operating modes (list vs. full-body drill-down). It does not, however, distinguish itself from siblings like ms_search or ms_chat, which an agent might reasonably confuse with mail retrieval.

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 explicit conditional usage for nearly every parameter: no message_id lists previews, message_id returns full body, folders:true lists folders, attachments with message_id lists attachments, filter for quick filters. It stops short of stating when NOT to use this tool (e.g., vs. ms_search for cross-content search).

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