Draft JSON-LD from a page

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

Annotations already mark the tool as readOnly, openWorld, and idempotent. The description adds useful behavioral detail: answers are trimmed to ~600 chars, extraction sources are specified, and 'all' returns every applicable block. This supplements the annotation profile without contradicting it.

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 a single dense paragraph but each clause earns its place: purpose, per-kind behavior, output caveat, and next step. It could be improved with light structuring, but it is not padded or repetitive.

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?

The description covers what the tool produces, the source data used, the answer-length caveat, and the draft-then-publish workflow. There is no output schema, but the expected JSON-LD constructs are named. Minor gaps remain around exact return structure and edge cases, but the tool is callable with confidence.

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 schema description coverage at only 25%, the description compensates by explaining the meaning of each kind value and mentioning organizationName's role for Article. It does not explicitly describe maxQuestions, though the schema's default/maximum and the FAQ extraction context make it reasonably inferable.

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 verb ('Generate') and resource ('draft JSON-LD from an existing page'), then enumerates concrete output types (FAQPage, Article/BlogPosting, breadcrumb). This makes the tool's role distinct from siblings like schema_validate or structured_data_audit.

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 clear context for each kind ('faq' extracts question-style headings, 'article' builds from metadata, 'breadcrumb' from URL path) and a follow-up workflow ('Review... then publish with wp_set_schema or by editing the site code'). It does not explicitly name when to prefer schema_validate over this tool, so it falls just short of full exclusion guidance.

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