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

Adds substantial value beyond annotations (which only say destructive/non-idempotent/open-world): it declares the operation free and spend-free, explains the stable clientRequestId contract, and warns that the native route has no durable request-ID receipt so the agent must re-read and never auto-retry. That recovery guidance directly informs safe invocation.

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 action, then states the boolean semantics, cost, and recovery caveat in tight sentences. The trailing "Fields: soclo://tools/soclo_ads_watch_ask_first_set." is cryptic filler that weakens an otherwise efficient layout.

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 simple boolean mutation with no output schema, it covers semantics, cost, idempotency caveat and post-uncertainty procedure. The unexplained `confirm` parameter and lack of any success/return signal are the only remaining gaps.

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?

With 0% schema coverage the description has to carry parameter meaning: it explains askBeforePause (true asks first, false uses normal pause rules) and the clientRequestId retention rule. However, the third parameter `confirm` is never mentioned, leaving a real gap in an otherwise compensating description.

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: "Change askBeforePause for existing Ads Watch configuration." The setting named (askBeforePause) is precise enough to separate it from the sibling auto-pause and generic watch-set tools without opening any schema.

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?

Gives concrete context for its use and directs the agent to read the current preference after any uncertainty rather than blindly retrying. It stops short of explicitly naming the read sibling or stating when to prefer it, so it is clear context rather than full when/when-not routing.

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