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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds a useful reinforcing constraint ('Changes nothing in the ad account') but discloses nothing further about rate limits, data freshness, or per-operation behavior, so it earns only modest credit above the annotations.

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 purpose and read-only guarantee are front-loaded in the first clause, and the long operation list, while duplicating the schema enum, does aid discovery of what can be requested. It is dense but not padded with filler.

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?

With no output schema and a nested free-form params object, the description covers the read-only nature and points to get_tool_schema, which is the minimum an agent needs. It does not describe the params object's structure or give any per-operation hints, so completeness is adequate but thin for a 23-operation dispatcher.

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 schema itself explains neither the free-form 'params' object nor the operation semantics. The description compensates by listing the operation values (redundant with the enum) and by pointing to get_tool_schema for an operation's parameters, which is genuinely useful routing, but it still leaves the shape and contents of 'params' opaque.

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+resource ('Microsoft Advertising, read-only operations') and enumerates the 23 concrete operations, then explicitly contrasts with the sibling write tool by noting 'Changes nothing in the ad account.' The one gap is that it does not distinguish this from other read siblings like get_performance or google_ads, but the read/write boundary with microsoft_ads_changes is clear.

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 description implies usage via 'read-only operations' and routes the agent to get_tool_schema for parameter details, which is a concrete next-step instruction. However, it never says when to pick this tool over alternatives such as get_performance, compare_periods, or the other platform read tools, and gives no exclusions.

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