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

Annotations declare readOnlyHint/destructiveHint=false, and the description reinforces this without contradiction by explaining why: the card's buttons perform the actual save/send, each gated by Keeploop permissions. That permission-check detail is genuine added context. It omits what the card returns and whether the draft is persisted after display, which is a real gap for an interactive tool.

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, no filler: what it is, what it does not do, then how to call it per mode. Every clause carries information an agent needs.

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 an output schema present, return values need not be described, and the interactive/permission model is covered. Remaining shortfall is the undocumented cc, reply_all and attachments parameters on an 8-parameter surface where the schema itself offers no descriptions.

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 coverage is 0%, so the description carries the full burden, yet it explains only 4 of 8 parameters (mail_id, sender, to, subject). The non-obvious semantics it does add are valuable – mail_id derives recipients from the referenced message rather than requiring them – but cc, reply_all, attachments and the required body are never addressed.

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 (show) and resource (email draft) plus the key mechanic: it renders an interactive card the user acts on. The line "Saves and sends nothing itself" cleanly distinguishes it from save_draft, update_draft and send_email, though it never names those siblings directly.

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?

"For a reply pass mail_id ...; for a new email pass sender, to, subject" gives explicit mode-selection guidance, which is the main branching decision for this tool. It stops short of saying when to choose show_draft versus save_draft/save_reply_draft, so the caller still has to infer the non-persisting preview intent.

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