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

The description explains why readOnlyHint is false: reading may 'refresh TikTok details if stale', which is a write to cached state and is genuinely additive beyond the annotations. It also discloses a data-validity limitation (public targeting data cannot establish effectiveness or sensitive traits). It does not cover auth requirements or refresh frequency bounds, so it falls short of 5.

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?

Two short sentences, no filler, with the core action and its side effect front-loaded. The caveat sentence earns its place by warning the agent against over-interpreting the returned targeting data.

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?

An output schema exists, so return values need no explanation, and the refresh behavior plus data caveat are covered. However, the two required identifiers are undocumented and there is no routing guidance against analyze_library_ad or search_library_ads, leaving real gaps for a tool with 0% schema description coverage.

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 description coverage is 0% for two required parameters, so the description must compensate and does not. brandId and adId are never explained, and the UUID/pattern constraints in the schema carry no human-readable meaning. 'Public ad' only loosely implies what adId identifies.

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?

Specific verb and resource: 'Read a saved public ad', plus the side effect of refreshing stale TikTok details. That distinguishes it from save_library_ad and delete_saved_ad, but it never contrasts itself with the close sibling analyze_library_ad, which also operates on a library ad.

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?

No when-to-use guidance and no alternatives named. It never says to prefer analyze_library_ad for evaluation or search_library_ads to locate an ad first. The only usable cue is the implied 'requires an already-saved ad' from the phrase 'saved public ad'.

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