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

Annotations already flag destructiveHint=true, idempotentHint=true and openWorldHint=true, so the lower bar applies; the description still adds real value by spelling out the spending/deletion approval gate, the requestId reuse contract, and the post-write status verification. It stops short of saying whether the goals array replaces or merges with existing goals, which is the most consequential unknown for a destructive update.

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 short sentences plus a field reference pointer, with purpose front-loaded and the safety flow immediately after. No sentence is filler, and the 'Fields: soclo://...' pointer is a compact way to signal where the full contract lives.

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 10-parameter destructive mutation with nested objects and no output schema, the approval and status-verification flow is covered but the core payload is not: what a 'goal' is, whether the array replaces the existing set, and how to interpret the operation status response are all left implicit.

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 the baseline of 3 applies; the schema already documents confirm, requestId, adAccountId, and the three expected* preview guards. The description only restates confirm/requestId semantics and says nothing about the nested goals array (category, origin, biddable) or the opaque platform/parameters fields, so it adds little beyond the schema.

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 account conversion goals') with account-level scope, which is a real distinction among the conversion-goal siblings. However, it never explicitly contrasts itself with soclo_ads_update_campaign_conversion_goals or soclo_ads_create_custom_conversion_goal, leaving the agent to infer the boundary from the word 'account' alone.

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 concrete procedural guidance: preview first, then an owner-approved confirm:true using the same requestId, and only report the change as live once status is active. What it does not give is any condition for choosing this tool over the campaign-level or custom-goal siblings, so routing among near-duplicates still requires guesswork.

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