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

Annotations declare readOnlyHint=false and destructiveHint=false, but the description does not explain what 'prepare' actually does: whether it merely stages a pending operation, whether any change is applied before confirmation, or what happens if the agent never calls confirm/deny. For a mutation-adjacent tool, the key behavioral fact (nothing changes until confirmed) is left unstated.

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?

The single sentence is front-loaded and free of filler, so it is efficient. However, its brevity here is under-specification rather than discipline — the space saved is space the agent needed.

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, which relieves the description of explaining return values, but the tool still carries 8 undocumented parameters and an unstated prepare→confirm/deny lifecycle. Given that complexity, one sentence is not enough for an agent to invoke it correctly.

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% across 8 parameters, and the description adds no parameter meaning at all. Worse, four overlapping names — creative_name, creative_names, new_creative_name, replacement_creative_name — are mutually ambiguous and the definition gives no rule for which to supply or whether they are alternatives.

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 phrase 'Prepare in-place library-creative swap on an existing ad' gives a specific verb (prepare) and resource (creative swap on an ad), which is enough to separate it from confirm/deny siblings by name pattern alone. It stops short of explicitly naming ads_replace_creative_confirm as its counterpart, so the workflow role must be inferred.

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 never states when to call this versus ads_replace_creative_confirm / ads_replace_creative_deny, nor that it is the first step of a staged approval flow. The only hint is the shared naming prefix in the sibling list, which is inference rather than guidance.

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