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

Annotations already declare the safety profile (not read-only, not idempotent, non-destructive). The description adds real behavioral value beyond them: last-write-wins semantics for concurrent edits to the same field, and patch-style 'omitted fields stay unchanged' behavior. It does not cover permission requirements or failure modes, so it stops short of a 5.

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 short sentences with zero filler; the core patch behavior is front-loaded and the concurrency caveat follows immediately. 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 not be described, and annotations cover the safety profile. For a 10-parameter mutation, the description adequately covers edit semantics and concurrency, but leaves permission/auth expectations and validation failure behavior unaddressed.

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 50%, so half the parameters carry no inline documentation. The description contributes the key patch semantics (only supplied fields are edited, omitted ones persist), which is genuinely useful, but it does not clarify any individual parameter (e.g. draft_id, subject, clearing behavior) to compensate for the coverage gap.

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 and resource ('Edit ... an unsent draft') and scopes it with 'supplied fields', which distinguishes it from create_draft (new draft) and send_draft (dispatch). The 'unsent' qualifier further separates it from sent-message update siblings.

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?

The description implies partial-update usage by saying omitted fields stay unchanged, but never states when to reach for this tool versus create_draft, delete_draft, or get_draft-first workflows, nor any prerequisites (e.g. draft must exist and be unsent). Usage is inferable rather than explicit.

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