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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is partly covered. The description adds genuinely non-obvious behavior: a required preview→owner-approval→confirm:true sequence keyed on a reused requestId, plus a note that the change only goes live once status is active. That is meaningful operational context beyond the annotations, though 'Claim live only when status is active' is cryptic without naming the status-check tool.

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?

It is short and the preview/confirm constraint is front-loaded, which is good. But the terse fragments ('Spending/deletion: preview, then owner-approved confirm:true...', 'Claim live only when status is active') trade clarity for brevity and leave the agent parsing telegraphic phrasing.

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, open-world mutation with 10 parameters, a nested payload and no output schema, the definition supplies the critical workflow (preview, approval, confirm, requestId reuse, status check) that an agent cannot infer from schema alone. The biggest remaining gap is the payload shape (goals/goalConfigLevel/customConversionGoalId) and how status recovery maps to soclo_ads_operation_status, which keeps it from a 5.

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 60%, so several parameters already carry their own meaning, and the description corroborates the confirm/requestId pairing. However, the nested payload (goals array, goalConfigLevel, customConversionGoalId) and the expected* guard parameters are not explained at all, and the 'Fields: soclo://tools/...' line is an unresolved pointer rather than usable parameter guidance.

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 description states a specific verb and resource ('Update campaign conversion goals'), which an agent can distinguish from read-side siblings like soclo_ads_get_campaign_conversion_goals. It does not, however, differentiate from closely named siblings such as soclo_ads_update_ad_conversion_goals or soclo_ads_update_custom_conversion_goal, so the exact scope (campaign-level vs account-level vs custom goal) is left slightly ambiguous.

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?

It gives real guidance for the mutation path: preview first, then owner-approved confirm:true with the same requestId. But it never says when to pick this tool over the sibling update/get conversion-goal tools, nor what prerequisites (campaign existence, goalConfigLevel choice) apply. Usage is implied rather than routed.

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