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

Annotations already declare destructiveHint=true and non-idempotent, but the description adds behavior the annotations cannot express: every call creates a user-approved proposal before anything changes, creates land PAUSED, and one account per call with no fan-out. These are exactly the mutation-safety facts an agent needs.

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-loaded with the scope and the routing exclusion, then the invocation shape, then the category list. The 13-tool enumeration is long but serves routing, so it earns its place; minor density cost only.

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?

There is no output schema, and the description fills that gap by explaining the proposal/approval response cycle. For a 3-param router with full schema coverage this is effectively complete, lacking only details like proposal expiry or error behavior.

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 it already documents action/tool_name/arguments. The description nonetheless adds the semantic constraint that 'execute is the only action', reinforcing the single-valid-value enum the schema implies but does not enumerate.

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 class ('create, update, pause or remove') and resource ('ChatGPT Ads'), scopes it precisely ('the 13 ... write tools'), and explicitly declares what it is NOT ('Reading, listing or checking anything is not here'). An agent can distinguish it from the chatgpt_ads read router without opening the schema.

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?

Gives explicit when-to-use and when-not-to-use: lookups belong to chatgpt_ads and 'calling this router to look something up is always wrong'. It also names the cheap alternative (chatgpt_ads(action="get_tool_schema")) for schema discovery.

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