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

Annotations already declare readOnlyHint and openWorldHint, so the description isn't carrying the safety burden, but it does add genuine operational context: the pagination caveat that cursor is only populated in Graph-API deployments while hasMore is the fallback signal, and an explicit 'Costs 2 credits.' Those are non-obvious behaviors an agent would otherwise discover only by trial.

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?

Four short sentences, purpose front-loaded, then data source, then the sibling-positioning cue, then the two operational caveats (pagination and credit cost). Nothing is redundant and nothing is buried.

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 12-parameter read-only tool with no output schema, the description covers the two things the schema cannot: how pagination behaves across deployments and the credit cost. It does not flag that most filters are optional beyond page_id, but the required field is declared in the schema, so this is a minor gap.

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 83%, so the schema already documents nearly every parameter (country requirement, political ad_type unlocking spend/impression fields, page_id accepting an Ad Library URL). The description adds only indirect cursor semantics tied to pagination and does not elaborate on limit, status, or date filters, so baseline 3 is right.

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+resource: 'All ads for one advertiser' / 'Ads a specific Facebook page is running or has run, from Meta's Ad Library,' and tags itself as the competitor-monitoring endpoint, which separates it from the keyword-oriented siblings like facebook_adLibrarySearch. It never names the nearest siblings (facebook_ad, facebook_adLibraryAdvertisers) explicitly, so differentiation is inferable rather than spelled out.

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?

The phrase 'This is the competitor-monitoring endpoint' implies a use case (watching a competitor's creative), but there is no explicit when-to-use/when-not or named alternative such as searching by keyword instead of by page. Guidance is implied, not stated.

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