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

With no annotations, the description carries the full burden and discloses important behaviors: the change is executed exactly once, and uncertain writes are recorded and never auto-retried. This gives an agent a clear model of the tool's side effects, though it omits details like failure response or whether explicit user confirmation is needed.

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, with the core action front-loaded. The second sentence adds a genuinely important behavioral caveat that 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?

For a one-parameter tool with no output schema or annotations, the description covers the essential invocation semantics and warns about retries. Minor gaps remain: the provenance of the approval_ref and the response shape are not addressed, but these are not critical for correct invocation.

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 0%, so the description must compensate. It does by clarifying that approval_ref is the single token to be consumed, implying it comes from a prior prepare step. The schema supplies the pattern and length, while the description adds the semantic role of a one-time-use reference.

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?

The description states a specific action—'Consume one approval_ref and execute the recorded delivery-status change once'—with a clear verb, resource, and single-use semantic. It differentiates from siblings like delivery_status_prepare and other *_confirm tools by naming the delivery-status scope.

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?

Use is implied through 'Consume one approval_ref', suggesting this is the confirmation step after a prepare operation, but the connection to delivery_status_prepare is never explicit. No when-not-to-use or alternative conditions are given, so the guidance is inferred rather than stated.

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