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

Annotations only say write/non-idempotent/open-world; the description goes well beyond by disclosing quota mechanics (one daily Ad Spy lookup, free same-day re-opens, allowance visible via `allowance` from sonar_ad_spy_competitors), the over-quota fallback (`meta.stale` plus `meta.note` to relay), and plan/auth prerequisites. No contradiction with readOnlyHint=false or destructiveHint=false.

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 write nature and the freshness trigger, then quota, fallback, and auth in descending priority; every sentence carries information. It is a single dense paragraph with stacked parentheticals, which costs a little readability but not content.

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 only two params, full schema coverage, and no output schema, the description covers what remains: return shape (same view as the sibling read tools), failure-mode payloads (`meta.stale`/`meta.note`), cost model, and authorization requirements. An agent can decide and call correctly from this alone.

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 both parameters are documented there, including the meta/tiktok enum meanings and the id source. The description only restates the provenance of `id` (from sonar_ad_spy_competitors) rather than adding new constraints, so the baseline of 3 applies.

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 first clause names a specific verb (refresh/fetch) plus the two resources (Meta ads, TikTok videos) and scopes it to stale cache. It explicitly tells the agent it returns the same view as sonar_ad_spy_ads / sonar_ad_spy_tiktok_posts, so the difference from those siblings is unambiguous.

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 states the trigger condition (cached copy over 24h old), the no-op case ('a fresher copy comes back unchanged and costs nothing'), and the free same-day re-open case. Alternatives are named directly via sonar_ad_spy_ads / sonar_ad_spy_tiktok_posts, leaving nothing material to inference.

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