Read Attachment Text

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

Annotations already establish readOnly, idempotent, non-destructive and openWorld, so the bar is lower, yet the description still adds real value: the mailbox.read privilege requirement, the not_found outcome from cache expiry or source deletion, and the instruction to inspect status/outcome before consuming text. It stops short of describing polling cadence or what a partially-converted state looks like.

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 tightly packed sentences with the workflow constraint front-loaded and zero filler. 'Check status and outcome before using text' is slightly compressed and could be clearer about which outcome values matter, but no sentence is wasted.

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?

An output schema exists, so return values need not be explained, and the description covers the prerequisite, the auth requirement, and the main failure mode. Given a five-parameter cached-read tool, that is nearly complete, with only the polling/retry expectation left implicit.

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%: mailbox_id, message_id, attachment_id, max_bytes and If-None-Match are all documented in the schema, including the default and cap on max_bytes. The description adds no parameter-level meaning beyond that, so the baseline of 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 or poll a previously requested attachment extraction') and explicitly rules out the conversion-starting behaviour, which separates it from request_attachment_text. It does not disambiguate against the near-identically named siblings mailbox_get_attachment and mailbox_read_attachment, which remain ambiguous from the description alone.

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 phrase 'previously requested' plus 'Check status and outcome before using text' tells the agent this is a follow-up step in a two-call workflow, not a first call. However, it never names mailbox_request_attachment_text as the prerequisite tool, so the agent must infer the alternative rather than being routed to it explicitly.

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