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

With no annotations, the description carries the full burden and does well: it discloses the important mutation side effect ('Fetching marks the message as read'), states that `attachments` is always an array and that one unreadable attachment never hides others, and gives the exact download route. It stops short of auth requirements or error behavior, so not a 5.

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 front-loaded sentences with no filler — return shape first, then the download route, then the side effect. The URL template is dense but earns its place by defining the attachment index.

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 simple two-param read tool with no annotations or output schema, this covers return shape, attachment handling, the write side effect, and how to retrieve files. What's missing is minor: the internal structure of `extracted`, pagination/size limits, and error cases.

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 0%, so the description must compensate. It doesn't explain `inboxId` or `messageId` formats, but the download path `GET /v1/inboxes/:id/messages/:msgId/attachments/:index` shows how those identifiers are consumed and introduces the `index` value for attachments, adding some meaning beyond the bare names.

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?

Specific verb (fetch) plus resource (one message) with explicit scope 'in full', and it enumerates what comes back (the `extracted` object and the attachment index). The contrast with `list_messages` is implicit in 'one message', so an agent can distinguish it from the listing sibling.

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?

Usage context is implied — call this when you need a single message's full content and its attachments. There is no explicit statement of when to prefer an alternative (e.g. `list_messages` for summaries, `extract_fields` for targeted fields), and no exclusions. The side-effect note about marking as read is usage-relevant but doesn't route the agent among siblings.

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