mailbox_get_attachment

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

Annotations only declare readOnlyHint=true, so the description carries the rest and does so richly: output content branches on MEPMAIL_MAIL_DOWNLOAD_DIR, saved files never overwrite, an inline override exists, a 512 KiB ceiling applies, and returned bytes are untrusted data that must not be opened or followed. This is exactly the behavioral context annotations cannot express.

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 tight sentences, front-loaded with the operation and its inputs, then return contract, then the safety caveat. Every clause carries information; nothing is padding.

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 must describe returns and does: filename, bytes, sha256, plus the environment-dependent saved_to vs content_base64 behavior and the size limit. Nothing needed to call or interpret the tool correctly is missing.

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 the baseline is 3, and the description genuinely adds meaning beyond it: it explains the provenance of id/revision/index and ties the environment variable to the saved_to vs content_base64 branch, which the schema only states for the inline parameter.

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?

Starts with a specific verb+resource ('Get one attachment of a message') and immediately anchors it to the sibling that supplies the required identifiers ('the message id and revision from mailbox_read_message and the attachment's index there'). An agent can distinguish this from mailbox_read_message without opening either schema.

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?

It tells the agent where the mandatory inputs come from (mailbox_read_message's id, revision, and attachment index) and the inline parameter's schema description covers when to force inline content. There is no explicit when-not or named alternative for attachment retrieval, so it stops short of a 5.

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