outlook_read_messages

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

The readOnlyHint annotation covers the read-only nature, and the description adds useful behavioral details: ordering follows input message_ids, partial 404s are surfaced in failures, and the call does not fail entirely. Minor gap: no mention of auth requirements or rate-limit consequences beyond the $batch cap.

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 tight and well-structured, with a clear purpose, return shape, example, and limit. The formatting is efficient and every sentence adds relevant information.

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 bulk read tool, it adequately covers return shape, partial failures, ordering, and limits. It does not provide an output schema, but the return keys are listed and the per-message shape is delegated to a sibling tool, which is reasonable given the context.

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?

The schema has no parameter descriptions, and the description only partially compensates. It explains message_ids ordering and references outlook_read_message for format, concise, and include_deferred_send semantics, but does not define those parameter values or effects directly.

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 clearly states the tool's purpose: bulk reading up to 20 messages by ID via $batch. It explicitly distinguishes itself from the single-message counterpart by saying to use this instead of N individual outlook_read_message calls.

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 provides explicit usage guidance by naming the alternative (outlook_read_message), stating the hard cap of 20, and noting partial-failure tolerance. This makes it clear when this tool is appropriate.

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