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

Annotations already declare readOnly/idempotent/openWorld, so the safety profile is covered, and the description adds useful behavior beyond them: website pre-fill of details, and that output includes both the <script> tag and 'checks to fix before publishing.' That validation-feedback loop is meaningful context an agent could not infer from the schema. It stops short of describing failure modes when the URL cannot be fetched.

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 short sentences, each doing distinct work: what is built, the pre-fill behavior, the return payload, and the invocation trigger. Output contract and trigger are front-loaded enough that an agent can act after one read.

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 22-parameter, zero-required, no-output-schema tool, the description covers the essentials: what gets produced, that everything is optional and filled from the site when possible, and what comes back. It does not flag the FAQPage-markup side effect of faqs (only the schema does) or note that no required fields means a bare call is valid, leaving minor gaps.

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?

With 22 parameters at 45% schema description coverage, the description carries real weight: it names address, phone, hours, service area, services, social profiles and optional FAQs, and explains the pre-fill behavior of the url parameter. However, roughly half the parameters (latitude/longitude, founding_year, price_range, logo/image URLs, business_name) get no clarification beyond their names, so it only partially compensates.

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 artifact ('Builds ready-to-paste Organization or LocalBusiness structured data (JSON-LD)') and enumerates the entity fields it covers, so the agent knows exactly what is produced. It does not name the closest sibling (generate_boilerplate_schema) to draw the boundary between generic boilerplate and business-specific schema, so it stays a clear-but-undifferentiated 4.

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 an explicit trigger condition tied to a sibling tool's output: 'Use it when an audit shows missing business schema,' which chains naturally from audit_ai_visibility. No alternatives or when-not-to-use cases are stated, but the invoking context is unambiguous.

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