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

Goes well beyond the annotations by disclosing the confirmation-mode exception, read-only mode, soft-limit confirmation versus hard-limit refusal, the side effect that pausing the only active ad stops the whole ad set, and the instruction to read `result` rather than assume success. These are exactly the operational traits an agent needs before a mutation call and are consistent with destructiveHint=true and openWorldHint=true.

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 action and its scope are front-loaded, which is good, but the paragraph repeats itself: 'happens at once' appears twice and the need to read `result` is stated three separate times ('the result says so', 'the result says what Meta now reports', 'Read `result` before saying what happened'). Tightening would preserve all the information in roughly two-thirds the length.

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 two-parameter mutation tool with no output schema, the description covers safety, timing, failure modes, and the existence of a `result` field an agent must inspect. The main residual gap is the undocumented `entity_id` semantics, but overall an agent has enough to call this correctly.

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 50%: `reason` is documented in the schema, `entity_id` is bare. The description adds only indirectly that entity_id may be a campaign, ad set, or ad, without specifying ID format or how to obtain it. Baseline 3 applies since half the schema does the work, but the entity_id gap is left unfilled.

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 and resource with scope: 'Pauses a campaign, ad set or ad in Meta.' An agent knows exactly what the tool does and on which entity types. It does not name the counterpart resume tool (e.g. switch_on) to sharpen the boundary, so it stops short of full sibling differentiation.

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?

'Use it when the person asks, or when they agreed to your recommendation' gives a concrete trigger condition rather than a vague intent. The limit/confirmation paragraph further explains when the call will execute immediately versus wait or be refused. No explicit 'when not to use' or named alternative is given.

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