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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful state semantics beyond that: reading is not sending approval and the draft stays editable until submitted, which tells the agent no mutation occurs. It does not cover failure behavior for a missing or stale draft_id.

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?

Two sentences, no filler, front-loaded with what is retrieved before the clarifying note about approval semantics. Every clause earns its place.

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?

An output schema exists, so return values need no prose, and annotations carry the safety profile; the description covers purpose and the read-vs-send distinction. It is complete enough to call correctly, with only error/not-found behavior left unstated.

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?

The single draft_id parameter has 0% schema description coverage, though its uuid format and pattern are machine-encoded in the schema. The description never mentions the parameter, but its meaning is self-evident for a get_draft tool, so this lands at the minimum-viable baseline.

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 ('Retrieve') and resource ('saved draft') and enumerates the returned content (recipients, bodies, reply target, attachment bytes), which implicitly distinguishes it from list_drafts. It stops short of naming any sibling explicitly, so an agent must still infer the by-id vs. list split.

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 review or continued work' and 'Retrieval is not sending approval' give contextual framing and quietly separate this from send_draft. There is no explicit guidance on when to reach for get_draft over list_drafts, nor any prerequisite such as needing a known draft_id.

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