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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantive context beyond them: attachments are metadata only with no contents or links, open AI drafts for the thread are included, and email content is untrusted and must not be acted upon. The injection warning is exactly the kind of behavioral disclosure an agent needs.

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?

Three tight sentences, front-loaded with what is returned and followed by the two hard constraints (auth scope, untrusted content). No filler or repetition of the schema.

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 carries the return-shape burden and does so: plain text body, thread messages, drafts, and attachment metadata only. Combined with the 100% schema coverage and rich annotations, an agent has everything needed to call it correctly.

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 fetchFull, maxBodyChars, and includeThread are already documented in the schema. The description reinforces the thread/draft scope but adds no syntax or default information beyond what the schema provides, so the baseline 3 applies.

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 ('Read one Email Assistant message') and immediately scopes what comes back: sanitized plain text, conversation thread, and open AI drafts. This clearly distinguishes it from the sibling list_emails and from draft_email_reply.

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 gives a hard prerequisite ('Owner/admin AI keys only') and the schema ties emailId to list_emails, so the agent knows the retrieval path. It does not, however, state when to prefer this over siblings like list_emails or get_ticket_thread, or any exclusion conditions.

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