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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile needs no restatement. The description does add genuine value by disclosing the return shape (body as text, attachment names only, not attachment contents) and a cost signal ('Free'), though the duplicated 'Free. Free.' reads as an artifact rather than intent.

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?

It is short and front-loads the returned fields, but it is a sentence fragment and the repeated 'Free. Free.' wastes one of only two sentences. The duplication is a defect rather than emphasis.

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-value burden and partially meets it (sender, recipients, body text, attachment names). It omits what happens when the message_id is invalid or the message is not found, and does not clarify the mailbox fallback behavior that the schema only lightly covers.

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 50%: mailbox is documented in the schema, but message_id has no description and the description supplies no hints about its format, source, or how to obtain it. This is the key parameter for the tool, and neither structured field nor prose explains it.

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?

With the title, 'One message in full: sender, recipients, the body as text and its attachments' names' clearly identifies a single-message read and even enumerates the returned fields. It does not, however, distinguish this from sibling google_mail_search, m365_mail_read, or email_get_message, so only the resource scope (Gmail, single message) separates it.

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?

There is no statement of when to use this versus google_mail_search (to obtain a message_id) or the m365 equivalent. An agent must infer from the sibling names alone that search is the discovery path and this is the fetch path.

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