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

Annotations only cover the read/write/idempotency flags; the description adds real behavioral context beyond them — the claim gate that a new draft would face, the immutability of sent and discarded drafts with the rationale for each, and an explicit 'Effects: draft text replaced; it remains unsent' line.

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?

Front-loaded with the core action and organized into scannable blocks (when to use, sent, discarded, effects). It runs long for a 4-parameter tool and the capitalized emphasis is slightly repetitive, but nearly every line carries a rule the 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?

No output schema exists, and the description covers state constraints, the claim gate, and the resulting effect, which is nearly everything needed to invoke it safely. It omits what the call returns and whether the prior body is archived anywhere, which an agent composing follow-ups would benefit from.

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 100%, so the baseline is 3; the description still adds meaning by framing the call as a partial update ('Pass only what changes'), which confirms that unset fields like subject or rationale are left alone. It does not clarify whether the replaced text is retained anywhere for the reviewer.

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?

Opens with a specific verb+resource+scope: 'Rewrite a draft that has not been sent. Pass only what changes.' The sent/discarded state rules implicitly separate it from crm_draft_message (new draft) and crm_drafts (listing), but no sibling is named explicitly, so an agent must infer the routing.

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?

Explicitly states when to use it ('USE THIS WHEN THE ANGLE CHANGES rather than discarding and starting again') and enumerates the triggering situations. It also gives when-not conditions with the correct alternative behavior: follow-up for sent drafts, fresh draft for discarded ones.

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