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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is largely covered. The description's 'Read only; no spend' reinforces this and adds the cost-free framing, but offers no additional behavioral detail such as auth requirements or response shape.

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 tight sentences plus a resource pointer, front-loading the read scope before the field enumeration. No filler, though the trailing 'Fields: soclo://...' reference is cryptic and adds little actionable content.

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 tool with no output schema, the description should clarify what targeting data comes back, but it only lists categories of fields via URI rather than describing return structure. Annotations cover the safety side, but input and output expectations remain thin.

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?

With 6 parameters at only 50% schema coverage, the description contributes nothing about inputs at all—no mention of accountId, the nested parameters.campaignId, confirm, requestId, or platform. Several parameters (platform, campaignId) are undocumented in both schema and description, so the description fails to compensate for the coverage gap.

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 (Read) and resource (a Google campaign's device/location/excluded location/language targeting), enumerating exactly what is retrieved. It effectively distinguishes itself from the mutation sibling soclo_ads_update_campaign_targeting via 'Read only', though it never names a sibling 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?

'Read only; no spend' implies this is the safe inspection path versus the update tool, giving implied usage context. But it never states when to prefer this over soclo_ads_get_campaign_details or search_ad_targeting, leaving the agent to infer the boundary.

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