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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior, so the safety profile is covered. The description adds useful behavioral context about scope (entire mailbox) and return type (summaries with subject, sender, received time, preview), but it does not delve into details like ordering, pagination, or query syntax. This mirrors the get_calls calibration example, which earned a 3 for adding scoping context but not richer behavioral detail.

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?

Two sentences with no filler: the first explains the action, scope, and output; the second gives usage guidance. Information is front-loaded and every clause contributes value.

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 simple search tool with annotations covering safety and a schema covering parameters, the description is nearly complete. It communicates return values (summaries with specific fields), scope (entire mailbox), and usage. It could mention default result limits or ordering, but those are already in the schema or are minor for selection and 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 100%, so parameter meaning is already fully documented. The description adds minimal extra semantic value for parameters—it refers to 'keyword' but does not explain query syntax or the 'from:' operator shown in the schema examples. Baseline 3 is appropriate because the schema carries the burden and the description does not expand on it.

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 ('Search'), a clear resource scope ('entire Outlook / Microsoft 365 mailbox'), and the output format ('matching email summaries'). It distinguishes itself from folder-scoped siblings like outlook_list_messages by emphasizing 'regardless of folder', making the tool's unique purpose obvious.

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 clear usage context: 'Use to find emails by topic, sender, or content regardless of folder.' This tells an agent when to invoke it, but it does not explicitly name alternative tools or say when not to use it, so it stops short of a full 5.

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