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

With no annotations, the description carries the full burden. It discloses supported formats, unsupported formats, the 10 MB size limit, and refusal behavior for non-file attachments. It doesn't state whether the operation is read-only or whether it downloads content, but the verb 'Open' and 'return what is in it' imply a read operation. The size limit and refusal behavior are valuable behavioral disclosures beyond what the schema provides.

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 front-loaded with the core action, then covers supported types, unsupported types, alternatives, limits, and parameter sourcing in a logical order. Every sentence adds information; there is no filler or repetition of schema fields.

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 tool with no output schema and no annotations, the description covers the key operational facts: what it returns, what it refuses, size limits, and where to get the required ID. It doesn't describe the exact return format for text vs. images, but the statement 'images come back as pictures the assistant can look at' gives enough for an agent to know what to expect. The main gap is not explaining messageId's role, but the overall context is strong.

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 only 33% (mailbox is described, messageId and attachmentId are not). The description compensates by explaining that attachmentId comes from get_outlook_message or get_outlook_conversation, which adds meaning. However, it doesn't explain what messageId is or how it relates to attachmentId, so the agent must infer that messageId identifies the parent message. This is adequate but not complete.

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 ('Open') and resource ('one attachment of an Outlook message') and clearly distinguishes this from sibling tools like read_gmail_attachment and save_outlook_attachment_to_onedrive. It also enumerates supported file types, which makes the tool's scope unmistakable.

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 explicitly says when to use this tool (to read supported attachment types) and when not to (PDFs, Excel, Word, attached emails, OneDrive links), and names the alternative save_outlook_attachment_to_onedrive for unsupported file types. It also tells the agent where to get attachmentId, which is actionable guidance.

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