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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and side-effect profile are covered. The description adds the meaningful dependency that the body must be derived from prior context rather than invented, but says nothing about rate limits, error behavior, or result shape beyond deferring to the schema.

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 identity and workflow position, then a numbered prerequisite list, then a caution. 'IMPORTANT: Always call step 2' restates step 2 almost verbatim, a small redundancy, but the emphasis is defensible for a hard prerequisite and nothing else is padding.

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?

An output schema exists, so return-value explanation is rightly omitted, and the workflow gating is well documented. However, for a tool whose only parameter is an unconstrained body object, the description leaves the actual payload structure entirely external; a minimal hint about the body's top-level fields would close the gap.

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?

The single 'body' parameter is a free-form object (additionalProperties: true) with 0% schema description coverage, so the schema itself conveys almost nothing about valid content. The description partially compensates by directing the agent to fetch the exact body structure via query_contexts request='actions_details' and to 'follow the schema exactly', but gives no inline indication of the body's top-level keys.

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 ('Query Microsoft Ads data') and positions the tool as the final step of a three-step workflow, which separates it from the context-gathering sibling. It never says what kind of data is returned or what query domains are supported, so the scope remains broad, but the function is unambiguous.

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?

Explicitly enumerates the two prerequisite calls on query_contexts (request='accounts', then request='actions_details' with actions from available_actions) and flags step 2 as mandatory before querying. An agent knows exactly what to do first, which sibling to call, and why – no inference required.

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