build_schema

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

With no annotations, the description carries the full behavioral burden and does so well: it discloses that it is pure templating with no model call, that the body carries no H1 by default unless BODY_INCLUDES_H1=true, the exact output shape (`paste_block`, `meta`), and the concrete conditions that populate `validation.issues`. It also explains the coupling guarantee (head, schema, and body cannot drift apart).

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 procedural directive is front-loaded and the dense bullet-style field spec is justified given five complex parameters at 0% schema coverage. It is long, but nearly every line conveys a constraint an agent needs, with minimal redundancy.

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?

There is no output schema, so the description must describe returns, and it does: `paste_block` (JSON-LD scripts plus body), `meta` for save_and_present, and `validation.issues` with named mismatch types. Given the nested-object complexity and required-parameter count, the definition is complete enough to call 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 description coverage is 0%, so the description must compensate and it does: it documents each field of `article` (headline, a 110-160 char description, exactly-two intro, 4-6 sections, a cta that must contain CTA_LINK_TEXT verbatim, plus optional fields), `faq` (4-8 entries), `image` (url/alt/title/caption with a public-https URL requirement), `references` (real fetched URLs only), and `keywords`. This adds far more meaning than the bare nested schemas provide.

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 action (render the HTML body and both JSON-LD blocks, then validate them) on a specific artifact. It explicitly positions itself in the pipeline as 'Step 9' and distinguishes its output from the sibling save_and_present, which consumes its `meta`. An agent can tell what this produces without opening the schema.

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?

Clearly establishes when this runs (step 9, after drafting) and what to do with the results: pass `meta` to save_and_present, and re-call after fixing a non-empty `validation.issues` list. It does not name an explicit alternative tool for a different platform, so it stops short of full when/when-not guidance.

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