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

Annotations already flag destructiveHint=true and readOnlyHint=false; the description adds real context beyond that: the rule applies to current and future ads, hand-set tags still win, and results report a match count with examples. It also clarifies that dry_run avoids persistence and that data is stored in Go Shift only. It doesn't describe what happens to existing tags if a rule is removed or replaced, which is the one behavioral gap for a destructive operation.

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?

Purpose is front-loaded in the first clause, followed by syntax, then behavior, then dry_run. Dense but nearly every sentence carries distinct information. The example list is slightly long, and the storage note is minor, but nothing is redundant.

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 7-parameter tool with no required params and no output schema, the description covers the critical paths (set, test, read, remove) and sketches the return value as a match count with examples. Gaps remain around error handling for invalid patterns and how account/platform interact with the folder scope.

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 86%, so the baseline is 3; the description earns above that by explaining placeholder syntax and separators with two worked examples and by defining {skip} as an ignored segment. It also explains the omit-pattern behavior and the meaning of dry_run. It adds little for account, platform or language, but the pattern parameter — the hard one — is well covered.

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 gives specific verbs (set, test, remove) tied to a concrete resource (the naming rule of one Meta/TikTok/Snapchat ad account) and explains the mechanism — a pattern that reads angle, hook and format out of ad names. It is clear what the tool does. It does not, however, distinguish itself from plausible siblings like creative_tags or meta_create_rule, leaving the agent to infer the boundary.

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 covers the main usage modes: supply a pattern to set a rule, dry_run=true to test without saving, remove to delete, and omit the pattern to read the current rule. It also states the precedence rule that manual tags win. What's missing is an explicit statement of when to prefer this over the sibling tagging tools.

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