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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds genuinely new behavior: returns TEXT metadata only, deliberately excludes images/videos to avoid token blowup, and results are cached for 7 days — all decision-relevant. No mention of rate limits or failure modes.

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?

Dense and front-loaded with the core action first, and nearly every clause carries information. The opening fragment ('Competitors' ads in the Meta Ad Library (texts and dates)') is partly redundant with the following sentence, and the telegraphic style ('Cache 7 days.') reads as notes rather than prose.

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 six optional parameters and no output schema, the description usefully enumerates return fields (ad copy, headline, CTA, start date, is_running, countries). Missing are account-level requirements for ad_account_id and any note on result pagination or empty-result behavior, though neither is critical for a read-only search.

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 83%, so the schema already documents page_id as preferred and search_terms as the fallback, plus limit defaults and country codes. The description's 'by brand/page or keyword' largely restates that, adding only light reinforcement of the mutual-exclusivity intent rather than new semantics for the six parameters.

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 ('Search the Meta Ad Library for competitor ads') plus the two lookup modes (brand/page or keyword). It is clearly distinguishable from sibling ad tools like get_ad_creatives and list_ads, which operate on the user's own account rather than the public competitor library.

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?

Gives real context: 'Use for Competitor Ad Analysis prompt', page_id preferred over keyword search, and the 90+ days = validated winners heuristic for interpreting results. It does not explicitly name an alternative sibling or state when not to use it, which keeps it short of a 5.

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