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

Annotations only declare the generic profile (not read-only, not destructive, not idempotent, closed world). The description adds information the annotations cannot: an extra scope requirement (message.read), the exact state transition (back to Drafts), and the timing precondition under which the call fails. It also reassures on blast radius by ruling out permanent deletion, which is precisely the ambiguity a cancel operation raises.

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?

Five short sentences, each carrying distinct information: permission to act, effect, auth need, argument provenance, failure condition, and scope exclusions. The most important constraint, the explicit-request gate, is front-loaded. Nothing is redundant with the schema or annotations.

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 three-parameter mutation with no output schema, the definition covers who may trigger it, what it consumes, what it changes, and when it fails. The only gap is the return payload: it implies the message lands in Drafts but does not say what the call returns or how a mid-flight failure surfaces, which with no idempotency guarantee is worth a sentence.

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 carry parameter meaning, and it does the most valuable part: it tells the agent that scheduleId and version come from list_scheduled_messages, which explains the otherwise cryptic 'version' integer and its provenance. mailboxId is left unexplained and no format or constraint details are added, so it stops short of full compensation.

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 (cancel) and resource (a scheduled message) plus the concrete resulting state: 'return it to Drafts.' That distinguishes it cleanly from list_scheduled_messages and from the delete_mailbox_draft/delete_folder siblings, which remove things rather than reverting them to draft.

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 an explicit gating condition ('Only when the user explicitly requests it'), a prerequisite action that supplies the arguments ('Pass ID and version from list_scheduled_messages'), a failure boundary ('Fails once sending has started'), and negative scope ('Never sends, reschedules or permanently deletes'). When-to-use, what-to-do-first, and what-not-to-expect are all covered.

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