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

Beyond the read-only/idempotent/non-destructive annotations, the description discloses that nothing is modified, that checks are skipped when no base URL is set, and that translations get no benchmark or cannibalization checks. It also states the result shape (statuses good/ok/bad/na, semantic coverage, prioritized fixes), adding real behavioral context.

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 description is dense but every sentence earns its place: scope, check categories, conditional advanced analysis, locale behavior, return format, base-URL exception, and website_id guidance. It front-loads the core computation and maintains a logical flow from normal behavior to exceptions.

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 three-parameter tool with an output schema, the description covers all relevant edge cases: translation scoring, multi-website accounts, absence of advanced analysis, missing base URL, and the free/non-destructive nature. Nothing essential for an agent to invoke it correctly is missing.

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?

Although the schema already covers all three parameters, the description adds decisive semantics: locale means scoring a translation against its localized keyword with benchmark and cannibalization disabled, article_id refers to saved article content, and website_id is needed only when an account has multiple websites. This goes beyond the schema's lexical 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 opens with a specific verb+resource: it computes the on-page SEO score of an article from saved content, including a concrete 0-100/S+ to D grading scale. It further separates itself from the run_advanced_seo_check sibling by explaining when that analysis affects this tool's benchmark output, so an agent can tell it apart.

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 concrete calling context: pass locale to score a translation instead of the default article, pass website_id only for multi-website accounts, and expect a competitor benchmark only when advanced analysis exists. It does not explicitly list exclusionary criteria versus check_seo_score or other siblings, but the conditions are clear enough for correct selection.

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