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

Annotations already cover the safety profile (readOnly, non-destructive), so the description's real value is the behavioral detail it adds: a missing provider connection returns a not_connected result rather than erroring, and the call goes out to the provider's live API. That failure-mode disclosure is exactly the kind of info annotations cannot convey. It doesn't cover latency, rate limits, or partial-provider failures.

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?

Three short sentences, front-loaded with what the tool returns, then the failure behavior, then the routing hint. Every sentence carries distinct information — nothing restates the name or the annotations.

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?

No output schema exists, so the description must sketch the return shape, and it does: status, daily budget, ad sets, plus the not_connected sentinel result. With one enumerated parameter and a clear read-only annotation set, this is nearly all an agent needs. A little more on what an ad-set object contains or pagination would push it to 5.

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 required parameter with full schema description coverage and a seven-value enum, so the schema fully documents 'provider'. The description adds nothing about provider selection or what happens with the 'test' enum value. Baseline 3 is appropriate when the schema carries the parameter semantics alone.

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 names a specific resource and the fields returned (status, daily budget, ad sets), and combines with the title 'List live ad campaigns' to make the verb and scope unambiguous. It falls just short of a 5 because the opening clause is elliptical — 'Campaigns read live from a connected ad platform' — rather than stating the action outright.

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 routes the agent away from this tool for a specific case: 'prefer get_acquisition_report for historical numbers.' That is a named alternative with the condition that selects it. It does not state when-not to call it for any other reason (e.g., missing provider auth beyond the graceful not_connected path), so it stops short of full when/when-not coverage.

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