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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context: each call is a live lookup (so results are not cached), a tier gate ('Pro and above'), and that results render as cards in a panel in Claude and ChatGPT. It stops short of describing result volume or failure modes, so it is strong but not exhaustive.

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-loaded with the core action, then the alternative, then the operational caveat and tier requirement. Every sentence carries distinct information — no filler, no repetition of the schema.

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 three-parameter read-only search with no output schema, the description covers what is searched, how results are surfaced (cards in a panel), the tier requirement, and the sibling boundary. Nothing an agent needs in order to call it correctly is missing.

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 100%, so the baseline is 3. The description's query examples (keyword vs. store domain) restate what the schema already documents, and it says nothing about the country enum or the limit cap of 20, so it adds no meaning beyond the schema.

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 ('LIVE FACEBOOK AD LIBRARY SEARCH: active Facebook and Instagram ads right now') and gives concrete query examples, so the agent knows exactly what is returned. It also explicitly distinguishes itself from the sibling find_ugc_ads, which handles person-to-camera UGC ads.

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 covers both accepted query modes (keyword or store domain) and names the alternative tool with the condition that selects it ('For person-to-camera UGC ads use find_ugc_ads instead'). It also adds a usage constraint — search once per question rather than repeatedly — which prevents redundant live lookups.

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