Read Attachment Text

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

Annotations already declare readOnly, idempotent, non-destructive, open-world, so the safety profile is covered. The description adds real value beyond that: the required mailbox.read scope, the guarantee that no conversion is triggered, and the not_found failure mode from cache expiry or source removal. It does not describe truncation behavior when max_bytes clips the text, which is the one remaining behavioral gap.

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?

Four short sentences, front-loaded with the action and precondition, then permission, then failure mode, then a usage warning. No sentence is filler and nothing is buried.

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 read-only poll tool with an output schema, the description covers prerequisites, permission, and failure semantics, which is enough to call it correctly. The only shortfall is that it gestures at 'status and outcome' without saying what states exist, relying on the output schema to explain them.

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 all five parameters including max_bytes limits, mailbox_id scoping, and If-None-Match are already documented. The description adds no parameter-level detail beyond a loose reference to 'status and outcome'. Baseline 3 is appropriate when the schema does the heavy lifting.

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 pair (read/poll) and resource (a previously requested attachment extraction), and the clause 'does not start conversion' implicitly separates it from the sibling request_attachment_text tool. An agent can distinguish it from mailbox_get_attachment / mailbox_read_attachment without opening schemas, though the counterpart tool is never named.

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?

Gives clear when-to-use context (only for extractions already requested, as a poll) and an implied when-not (it will not begin a conversion). The 'check status and outcome before using text' line adds a sequencing rule. Naming the request tool explicitly and stating what to do on not_found would push this to a 5.

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