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

Annotations only declare read-only/non-destructive/open-world; the description adds real behavioral content beyond that: bid adjustment semantics ('+20 = bid 20% more, -100 on a device = excluded'), an exclusion flag, 'a type with nothing set has no restriction', and the campaign-vs-ad-group override rule. It stops short of describing result shape or volume, but the interpretation guidance is substantive.

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?

Three sentences, the primary purpose and scope front-loaded, followed by result interpretation and one inheritance rule. No filler, no restating of the title.

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 read-only 4-parameter list tool with an output-schema-free response, the description covers what is returned (criteria + bid adjustment + exclusion flag) and the campaign/ad-group precedence. Only pagination or result-size expectations are missing.

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 the schema already documents types, accountId, adGroupId and campaignId, establishing a baseline of 3. The description reinforces the key semantic that adGroupId redirects the read to ad group-level targeting and adds the override relationship between the two levels, giving it a slight edge over the schema alone.

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 ('List') and resource ('targeting and bid adjustments') and enumerates the criterion types covered (locations, radius, device, day/time, age, gender). It also clarifies the two resource modes — campaign by default, ad group when adGroupId is given — which cleanly separates it from siblings like set_campaign_targeting, msads_set_bid_adjustment, and msads_get_campaign_criteria.

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?

'...or an ad group's when adGroupId is given' tells the agent the exact condition that switches the read target. However, it never names the alternative tool for changing targeting (set_campaign_targeting) or for filtering criteria, leaving write-vs-read routing to inference.

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