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

Beyond the annotations, the description discloses meaningful behavioral traits: it charges 1 AI brain credit before work, refunds on provider failure, is synchronous and slow, has a 10-call-per-hour limit, fails and refunds when fewer than 2 ranking pages can be read, and requires an active subscription or free trial. This greatly exceeds what the annotations convey.

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?

Although lengthy, the description is dense and front-loaded: it leads with the core benchmarking behavior and report contents, then moves through operational constraints, failure modes, cost, rate limits, and alternatives. Every clause carries practical information that an agent needs before invoking the tool, with no filler.

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?

Given the tool's complexity, cost, latency, and external dependencies, the description covers all essential context: what it returns, what can cause failure, rate limits, billing, prerequisites, and how it differs from sibling tools. The presence of an output schema means the detailed return shape does not need to be restated, so the description is complete.

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?

The schema already documents all eight parameters with 100% coverage, so the baseline is 3. The description adds value by clarifying that content is passed inline, does not need to be in BlogSEO, and that website_id should be supplied when the account has multiple websites. These details go slightly beyond the schema descriptions.

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 states a specific action and resource: benchmarks caller-supplied content against Google's top organic results for a target keyword and locale, producing an advanced score and a competitor-relative report. It also differentiates itself from the sibling run_advanced_seo_check by clarifying that this variant works on inline content and raw HTML rather than stored articles with rendered pages.

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 description gives explicit usage direction: use check_seo_score first for a free on-page-only check, pass website_id when the account has several websites, and wait 1-3 minutes instead of retrying. It also explains when not to rely on the result, noting that JavaScript-rendered competitor pages are skipped and that results may differ from run_advanced_seo_check on stored articles.

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