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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is carried by structured data. The description adds real value by disclosing the hidden dependency chain and that the body must be derived from prior steps, but says nothing about rate limits, failure modes, or the size/shape of results beyond what the output schema covers.

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 workflow position and numbers the required steps, which is the right structure for a multi-stage prerequisite. Slight redundancy: the importance of calling step 2 is asserted twice ("REQUIRED: Complete these steps first" and "IMPORTANT: Always call step 2"), costing a line without adding information.

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?

Given one free-form parameter, an output schema that already documents returns, and a genuinely complex multi-tool workflow, the description covers the critical missing piece — where the body structure comes from. Adequate, though an inline minimal body example would close the remaining 0%-coverage 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?

There is a single free-form `body` object with additionalProperties:true and 0% schema coverage, and the description never names any field inside it. It only says "Rely on info from steps 1-2" and "Follow the schema exactly" — but the schema is an untyped bag, so the agent still learns nothing about the body's contents from this tool; it must run another tool to find out.

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 concrete verb and resource ("Query Facebook Ads data") and positions itself as the terminal step of a workflow, which is enough to distinguish it from query_contexts (discovery) and execute_action (mutation). What the query actually returns or which endpoint it hits is only implied via the prerequisite steps.

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 prescribes prerequisites: call query_contexts with request='accounts' first, then request='actions_details' with specific actions, and only then query. This is unusually directive about ordering. It stops short of stating when NOT to use this tool instead of execute_action, so sibling selection at the final step still requires inference.

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