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

Annotations only give the safety profile (not read-only, not idempotent, not destructive, closed-world). The description goes well beyond that: real API spend, a 24-hour per-country rate limit, the 429 semantics with nextScanAvailable, and the fact that the call blocks 30-90 seconds before returning only a summary.

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 tight sentences, each carrying distinct information (what, eligibility, cost/rate limit, blocking behavior plus hand-off). The most decision-relevant constraint, Pro+ and 24h staleness, is front-loaded.

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 blocking mutation with no output schema, it covers everything an agent needs: eligibility, cost, rate limit, error semantics, latency, and where to read the full results. No return-value explanation is required since it explicitly delegates to get_seo_snapshot.

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% for the single 'site' parameter, so the schema already documents it. The description's phrase 'every selected country' hints at a selection concept that is not represented in the schema, but it adds no syntax or format detail for 'site' itself. Baseline 3 applies when the schema does the work.

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 (runs) and resource (SEO Analysis scan), enumerates what the scan covers (DataForSEO ranked keywords, opportunities, Lighthouse), and scopes it to 'every selected country that is stale'. It also names the sibling tool for reading results (get_seo_snapshot), so an agent can separate it from run_keyword_research or run_ai_mentions_scan without opening schemas.

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?

Explicit preconditions: Pro+ only, countries must be stale, once per 24 hours per country. It tells the agent what a 429 means ('nothing is stale yet') and where to find the alternative (get_seo_snapshot for details), which is exactly the when/when-not/alternative guidance needed.

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