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

The annotations already establish a safe read, so the description instead spends its space on non-obvious behavior: the resolution precedence (running experiment > live > none) and the silent-failure mode where a nonexistent placement 'renders nothing at all, with no error'. It also discloses how the list is built (configured ∪ observed), which is exactly the kind of context annotations cannot carry.

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 sentences, front-loaded with what is returned and then escalating to the 'IMPORTANT' warning. The precedence notation ('running experiment > live > none') compresses a rule that would otherwise need a paragraph. Nothing 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?

With no output schema, the description must describe return values, and it does: surfaces, per-placement serving state, and the valid placement names. It stops short of saying what identifying fields accompany each paywall/onboarding entry (ids, status) that an agent would need to chain into `get_paywall_doc` or `get_onboarding_doc`, leaving a small 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 tool takes zero parameters, so there is no parameter semantics to document and the baseline of 4 applies. The description uses the space instead to characterize the output fields (`placements`, `observed`) that would-be parameters relate to.

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 verb-and-resource pair ('Every paywall and onboarding flow' plus the placement list) and states what the tool resolves per placement ('running experiment > live > none'). It is clearly distinguishable from the singular sibling `get_surface` and from draft-creation tools.

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?

It gives an explicit when-to-use instruction: read `placements` before writing a placement string into code. That is a clear trigger condition. It does not name sibling alternatives (e.g. `get_surface` for a single surface), so it falls short of a full when/when-not/alternatives statement.

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