microsoft_list_emails

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

Annotations already disclose readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds the important quirk that `effect` is required and must be 'read', with Spring verification, plus an approval_ref parameter 'when resuming a write.' However, it does not mention pagination, ordering, default folder behavior, or error characteristics, so the additional context is limited but not contradictory.

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 well-structured: a one-sentence purpose followed by a terse arg list. Every line earns its place, especially given the lack of schema property descriptions. It is not padded, though the mechanical arg formatting keeps it slightly below a perfect 5.

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?

An output schema exists, so return values need not be explained. The main gap is the set of platform plumbing parameters (project_id, project_ref, connector_account_ref, idempotency_key, approval_ref) whose role, requiredness, and relationship to a simple read/list operation are not explained. The schema provides defaults and the required effect const, but the description still leaves an agent guessing about when and how to populate these fields.

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 argument list must compensate. It does provide short descriptions for all nine parameters, with clear ones for folder, top, and filter. However, several refs like project_ref, connector_account_ref, idempotency_key, and approval_ref are described in vague platform jargon ('Exact project correlation reference') that an agent cannot confidently translate into actual values. It adds meaning beyond bare titles but doesn't fully clarify every parameter.

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: 'List Outlook messages in the connected Microsoft 365 mailbox.' This clearly indicates it is for reading emails from an Outlook/Microsoft 365 mailbox, distinguishing it from Gmail or channel/chat/drive siblings by name and domain, though it does not explicitly contrast those alternatives.

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 a clear action context but no explicit when-to-use, when-not-to-use, or alternative tool guidance. Siblings like microsoft_list_chat_messages and gmail_list_emails exist, but the description does not mention them or state exclusions. The intended use is implied by 'Outlook messages' and 'Microsoft 365 mailbox' rather than explicitly routed.

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