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

Goes well beyond the annotations by disclosing precedence rules ('Values the person gives win over values read from the page'), the heading-with-question-mark extraction rule for FAQPage, that reportUrl is kept 30 days and may be null, and exactly what is recorded versus never recorded (no IP, no page text). Annotation-consistent and unusually forthcoming on privacy and side effects.

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 purpose and usage, and each clause carries information, but the single dense paragraph bundles purpose, precedence, return shape, error behavior and data-recording policy into one block that is harder to scan than it needs to be.

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 no output schema, the description supplies the return shape (jsonLd, scriptTag, filledFrom, missing, existingTypes, plus summary and reportUrl) and error format, which is what an agent needs. Slightly compressed, but complete enough to call the tool correctly.

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%, so most parameter meaning is already carried by the schema. The description adds some value by stating the generic precedence rule and how page-derived defaults are sourced, but it does not explain individual parameters beyond that.

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 resource ('Drafts schema.org JSON-LD for a page') and enumerates the four supported types (Organization, WebSite, FAQPage, LocalBusiness), so an agent knows exactly what comes out of the call. It is distinguishable from siblings like check_page and draft_llms_txt, which address different artifacts.

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 trigger given: 'Use it when check_page reports missing or incomplete structured data,' which ties it directly to a sibling tool's output. It does not state when *not* to use it (e.g. when the page already declares complete markup), which keeps it just short of a 5.

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