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

Annotations already declare destructiveHint=true and openWorldHint=true, so the mutation/live-effect profile is known. The description adds genuinely new behavior: the approval_ref is single-use, dispatch happens exactly once, and uncertain outcomes must not be replayed. It omits failure semantics and any auth/rate constraints.

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 and the single-use constraint front-loaded and the fallback tool named at the end.

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 destructive, no-output-schema confirmation tool, the description covers the essential risky semantics (single-use, no replay, alternative on uncertainty). It could still say what the caller should expect on success or what the original route reference means.

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 parameter meaning. It explains approval_ref as a consumable single-use token (useful), but says nothing about connection_context, which is left entirely unexplained.

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 ('consume... and dispatch') and a concrete resource ('the exact recorded TikTok ad-group change'), plus a scope qualifier ('once'). It is clearly distinguishable from bid_prepare, though it never names that sibling or the other *_confirm tools explicitly.

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?

Provides a real when-not rule: do not replay on an uncertain result, and route to operations_get instead. It does not state the prerequisite (that bid_prepare must have produced the approval_ref) or contrast with budget_confirm/delivery_status_confirm, so context is clear but not fully bounded.

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