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

Annotations only declare readOnly/destructive/idempotent/openWorld flags; the description adds what the annotations cannot: the call consumes one of the user's remaining change credits (one free change included), the rebuild is asynchronous and takes minutes, and status must be polled via get_ad_status. That is meaningful operational context beyond structured data.

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?

Purpose is front-loaded, then cost, then the usage gate, then latency and follow-up — a sensible order with no filler sentences. Slight redundancy between 'a change the user asked for' and 'call it only when the user asked for this change' keeps it from a 5.

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?

Output schema exists, so return values need no explanation, and the description covers the async lifecycle and the follow-up tool. It does not say what happens when the quota is exhausted (error vs. refusal), which is the one gap for a credit-consuming mutation.

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 100%, so both ad_id and change are already documented, and the description largely restates the 'in their words' guidance. The only added nuance is the instruction to pass the request verbatim rather than paraphrased, which is minor. Baseline 3 is appropriate.

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 ('Rebuilds an existing ad') plus concrete examples of the change type (wording, colors, images), which clearly separates it from create_ad (new ad) and get_ad_status (poll status). An agent can tell what this does without opening the schema.

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?

Gives an explicit precondition ('call it only when the user asked for this change'), an argument-handling rule ('pass their request as they said it'), and names the follow-up sibling get_ad_status. The quota cost is presented as a reason to be conservative, which is exactly the kind of gate an agent needs.

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