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

Annotations only declare readOnly and openWorld; the description adds real operational context beyond them: a 500 KB ceiling, explicit stripping of scripts/styles/nav/footers/forms/comments, table flattening to text, and the baseUrl dependency for absolute links. It also discloses the $0.001 x402 charge and that failed calls are free – pricing and failure semantics the annotations cannot convey. It does not describe output shape, but an output schema exists.

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 core transformation and its element list come first, then behavioural caveats, then cost last. Dense but every clause carries information an agent needs – no filler or repetition.

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 two-parameter, read-only converter with a full output schema, the description covers input limits, transformation semantics, link resolution, and billing. Nothing needed to invoke it correctly is missing.

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 the baseline is 3; the description earns above that by explaining the consequence of baseUrl (relative links become absolute) and restating the 500 KB input bound in human units. That clarifies intent behind both parameters rather than merely echoing their types.

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 transformation (raw HTML in, GitHub-flavoured Markdown out) and enumerates exactly which elements survive and which are stripped. The phrase 'raw HTML you send' implicitly separates it from fetch-based siblings like reader_markdown_extract, so an agent can pick correctly without opening a 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?

The description makes the trigger condition clear: you use this when you already hold the HTML, and you must supply baseUrl if relative links matter. It stops short of naming an alternative tool or stating when not to use it, so no explicit routing guidance.

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