gmail_read_message

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

The description is transparent about behavior: it fetches only message-owned text bodies, excludes external images/resources and file attachments, and characterizes output as 'bounded, untrusted inert text.' It also implicitly signals no side effects (read-only), consistent with the readOnlyHint annotation. No hidden actions or limitations are omitted.

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 two sentences, direct and free of extraneous detail. It efficiently packs the core action, the resource boundary, and the output nature without padding or redundancy.

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 adequately explains the return shape: text content plus attachment metadata, and explicitly states what is not included (external resources, file attachments). It also conveys the trust boundary ('untrusted inert text'), giving the agent enough context to handle the result appropriately.

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 input schema has no property descriptions (0% coverage), so the description must compensate. It does partially: 'explicit account' implies accountId is a specific account identifier, and 'one message' implies messageId. However, it does not clarify the format, purpose, or constraints beyond the schema patterns, leaving some ambiguity for an agent.

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?

Clearly states the action ('Read one message'), the resource ('one message from an explicit account'), and the scope (text bodies plus attachment metadata). The mention of 'bounded, untrusted inert text' and the exclusion of external resources/file attachments uniquely distinguishes this from a generic message reader, though it does not explicitly name sibling tools.

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 implies usage for fetching a single message's text and metadata, which is reasonably clear. However, it does not explicitly guide selection among siblings like gmail_search or gmail_read_thread, nor state when not to use it (e.g., for attachments or threads). The phrase 'from an explicit account' hints at requiring accountId but provides no comparative guidance.

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