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

Annotations already cover the safety profile (readOnlyHint, destructiveHint=false, openWorldHint), yet the description adds real context: results follow Facebook ranking and are non-exhaustive, upstream restrictions/timeouts return uncharged errors, and videos[].is_paid_partnership is a nullable boolean that currently never returns false. That last point is genuinely valuable since no output schema exists. It loses a point for the contradictory credit statements ('Each successful search page costs 1 credit' vs 'Completed lookups cost at least 10 Nexscope credits'), which leave billing behavior ambiguous.

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?

The core text is front-loaded and useful, but the description is badly bloated: the entire paragraph is duplicated verbatim, and marketing boilerplate ('Facebook Search Videos API View Pricing ... 1 credit per request') is pasted in mid-text. The duplicated and conflicting credit-cost sentences force the reader to reconcile information rather than act on it.

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?

With no output schema, the description carries the return-value burden and does partially discharge it by naming cursor, has_more, and the videos[].is_paid_partnership null semantics. However, it never characterizes the rest of the video payload, so an agent still cannot anticipate what fields come back beyond those three.

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 100% and the cursor parameter's schema description already states 'Keep the query unchanged when paginating. Stop when cursor is null or has_more is false' — the description's pagination sentence is essentially a restatement. The query parameter gets no added semantics (no syntax, operators, or length constraints). Baseline 3 applies since the schema carries the parameter burden.

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 opens with a specific verb and resource ('Searches Facebook's native public video search') and immediately bounds the scope by naming what it is not: Google-indexed discovery and general Facebook text/photo-post search. That negation cleanly separates it from siblings such as social_facebook_post, social_facebook_group_posts, and social_instagram_reels_search.

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 gives explicit operational guidance: use a client timeout of at least 30 seconds, pass the returned cursor with an unchanged query for the next page, and stop when cursor is null or has_more is false. It also states the exclusions (not text/photo posts, not Google-indexed) so an agent knows when to route elsewhere.

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