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

Annotations already declare non-readonly, open-world, non-idempotent, destructive behavior. The description adds meaningful context beyond that: approval gating, reversible auto-policy limits, and the fact that created objects start paused with no spend. It does not cover auth requirements, rate limits, or return behavior.

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?

The description is front-loaded with the operation list and then immediately states the proposal/creation semantics. The long enum-like list is necessary for the tool's scope, and the remaining sentences are dense and purposeful.

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 complex 21-operation mutation tool with sparse schema coverage and no output schema, the description covers the key invocation context: operation list, proposal approval behavior, paused creation, and where to find per-operation parameters. A fuller definition would mention how to check approval/change status afterward, but the essentials are present.

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 0%, so the description must carry parameter meaning. It does provide a useful pointer ('Parameters of an operation: get_tool_schema'), but it does not itself explain the shape or required fields of the nested 'params' object, leaving the agent dependent on a separate schema lookup.

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/resource pair ('Microsoft Advertising, change operations') and enumerates all 21 supported operations. This makes it clearly distinguishable from the read-oriented 'microsoft_ads' tool and from generic change siblings like 'propose_change'.

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 clear usage context: changes to existing objects are proposals that require approval or auto-policy allowance, and newly created campaigns/ad sets/ads are paused. It does not explicitly name when to use this versus 'propose_change' or the read 'microsoft_ads' tool, so it lacks explicit alternatives/exclusions.

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