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

Annotations already establish readOnly and non-destructive, but the description goes well beyond them by disclosing the format support matrix, how each type is returned (images as viewable pictures), the 10 MB limit, and which attachment kinds are rejected outright. This is behavioral context an agent needs before calling and cannot derive from the annotations.

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?

Front-loaded with the core action, then format behavior, then limits and sourcing. Every sentence carries non-redundant information; no filler.

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?

With no output schema, the description still explains what comes back for each format and the boundary conditions (size, refusals, unsupported types). Nothing an agent needs to call it correctly is missing.

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 coverage is only 33% (mailbox documented, messageId and attachmentId bare), so the description must compensate. It does so for attachmentId by naming get_outlook_message and get_outlook_conversation as sources, but messageId is left to inference and the 10 MB note is not tied to any specific 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?

States a specific verb and resource ('Open one attachment of an Outlook message and return what is in it') and makes clear it is the read path versus the sibling save path. An agent can distinguish it from read_gmail_attachment, read_agentmail_attachment, and save_outlook_attachment_to_onedrive without opening any schema.

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?

Explicitly enumerates supported formats, the unsupported ones (PDFs, Excel, Word) with the alternative named (save_outlook_attachment_to_onedrive), the refusal cases (attached emails, OneDrive links), a size ceiling, and where to obtain the required attachmentId. When-to-use, when-not-to-use and alternatives are all covered.

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