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

"Changes nothing in the ad account" restates what readOnlyHint/destructiveHint already declare, so it adds little. Its one real contribution is the workflow note that per-operation parameters live behind get_tool_schema, but it says nothing about pagination, rate limits, or account-scope requirements for a tool marked openWorldHint.

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?

Front-loads the resource and read-only scope, then a single enumeration sentence, then the parameter-discovery pointer. Minimal waste, though the long inline operation list is dense and would read better as a compact bulleted or grouped listing.

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?

As a dispatcher with no output schema and zero schema coverage, the description does the essential work of enumerating operations and deferring parameter discovery to get_tool_schema. It remains incomplete on distinguishing snapchat_ads from snapchat_ads_changes and on what each operation returns, which an agent still cannot determine from the definition alone.

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 0% and the nested `params` object is entirely undocumented, so the schema carries no parameter meaning. The description partially compensates by listing the valid operation values and pointing to get_tool_schema for per-operation arguments, which is genuine routing value but stops short of describing what any operation actually requires.

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?

Names the resource (Snapchat Ads) and scopes it as read-only, then enumerates the thirteen supported operations, which is enough for an agent to distinguish this dispatcher from the write-oriented sibling snapchat_ads_changes. It never explicitly names that sibling as the mutation counterpart, so differentiation is implied rather than stated.

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?

The operation list maps tasks to entry points and the closing line tells the agent how to obtain parameters, which is useful routing guidance. However, there is no explicit statement of when to use this tool versus snapchat_ads_changes or the platform-agnostic siblings like get_performance, leaving selection partly inferential.

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