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

Annotations already cover safety (readOnlyHint, openWorldHint), and the description adds real context beyond them: the 1-credit cost, that results are derived from an underlying ad search rather than a native advertiser index, and that ranking is by number of ads run. It does not disclose caching behavior despite exposing cache_max_age, which keeps it from a 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?

Three tight sentences: purpose first, then result shape and the downstream page_id, then derivation/ranking, then cost. Every sentence adds a distinct fact with no filler.

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 read-only search tool, the description supplies purpose, output shape, the key field an agent needs elsewhere, ranking semantics, and cost — the practical gaps left are minor enum defaults the schema already encodes.

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 only 40%, so the description must carry weight; it clarifies that the query matches both advertiser names and ad copy and that the sample size drives advertiser breadth, but status, country, and cache_max_age get no explanation anywhere. Partial compensation only.

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 ('Find advertisers running ads') and immediately qualifies the output as 'distinct advertisers whose ads match a search term' ranked by ad volume. This is clearly distinguishable from siblings like facebook_adLibrarySearch (returns ads) and facebook_pageAds (takes a page_id), which the description explicitly links to.

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?

Usage is implied strongly: use this when you need advertisers matching a term, and it names the downstream consumer (/v1/facebook/ad-library/page-ads) that needs the returned page_id, which routes the agent correctly. It stops short of explicitly saying when to prefer facebook_adLibrarySearch instead, so no full 5.

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