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

Annotations already declare destructiveHint=true and openWorldHint=true. The description adds genuinely useful behavior beyond them: the single-use nature of approval_ref ('one'), the one-time execution guarantee, and the retry policy ('Uncertain writes are recorded and never auto-retried'). That retry disclosure is valuable context for a mutation 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?

Two tight sentences, zero filler, and the core action is front-loaded before the retry caveat. 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?

The behavioral story is solid for a destructive write tool with no output schema, but the 0% parameter coverage and the absence of any mention of connection_context or how to obtain an approval_ref leave the invocation path underspecified.

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 the burden. It only implies approval_ref is a consumed single-use token, and says nothing about connection_context or the token's origin/format, leaving the optional parameter entirely undocumented in both schema and description.

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: 'execute the recorded delivery-status change' via an approval_ref. The prepare/confirm pairing is implied by the approval_ref and the sibling delivery_status_prepare, but the description never names that sibling, so an agent must infer the workflow relationship.

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?

Usage is implied through 'Consume one approval_ref' and 'execute the recorded delivery-status change once', suggesting this is the second step after a prepare. However, it never states when to use this over alternatives like delivery_status_prepare or other *_confirm tools, nor any prerequisites beyond the token.

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