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

Annotations are empty, so the description carries the full burden. It discloses the core transformation behavior and output style, and even adds commercial traits like per-call pricing and no expiring credits. Still, it says nothing about authentication, error behavior, request format expectations, or whether the conversion is stateless/safe.

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 first sentence is efficiently front-loaded with the tool's core purpose and output details. The second sentence adds commercial context that is not needed for correct invocation, so it is slightly less valuable, but the overall description remains compact and scannable.

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?

Given an unusable generic input schema, no output schema, and no annotations, the description should compensate with operational details. It explains what the tool produces but leaves the agent guessing about the input structure, output format, page limits, and API requirements, so an agent could not reliably construct a valid call.

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 0% schema description coverage and a single nested `input` object allowing arbitrary property names and values, the description needed to explain how to supply HTML. It only says 'HTML to clean Markdown', which gives the semantic domain but not the expected shape, nesting, encoding, or whether `input` should be a string, object, or contain HTML content under a specific key.

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 clearly states the tool converts HTML to clean Markdown for LLM/RAG pipelines, even naming the supported elements (headings, lists, tables, links, code fences). It lacks an explicit imperative verb like 'convert', and the generic name 'run' adds no signal, but the resource and result are unmistakable.

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 phrase 'for LLM and RAG pipelines' implies the intended use case, and the pricing note suggests it is a standalone paid API. However, there is no explicit statement of when to use this tool versus alternatives, no exclusions, and no mention of input constraints such as HTML size limits or URL-versus-raw-HTML support.

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