html_to_markdown

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

With no annotations, the description must disclose behavioral traits itself. It does mention that it fetches URLs, removes scripts/styles/navigation, and produces clean markdown. However, it omits information about rate limits, error handling, whether dynamic content is supported, or the exact format of the returned markdown. It provides some useful context but is not comprehensive.

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, tightly written sentence that front-loads the primary action and includes all essential information without any filler. Every word contributes to understanding the tool's purpose.

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 simple tool with only two optional parameters and no output schema, the description covers the core functionality well. It explains the input types, the conversion process, and the cleaning behavior. The absence of a statement of return value is minor since 'convert to markdown' implies the output is markdown. However, given the sibling web tools, a brief note on when to use this specific tool would improve completeness, but it is largely adequate.

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%, with both parameters having clear descriptions ('URL to fetch and convert' and 'Raw HTML to convert (use instead of url)'). The description adds no new meaning beyond this—it merely restates that it accepts HTML or a URL. The mutual exclusivity is already conveyed in the schema via 'use instead of url', so no additional value is added.

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 ('Convert') plus the resource ('HTML content or a URL') and the output ('clean, readable markdown'). It also specifies what is removed (scripts, styles, navigation), making it clearly distinct from sibling web extraction tools which would not produce markdown.

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 implies the tool is used when you have HTML or a URL and want markdown, but it does not explicitly contrast with sibling tools like web_extract or web_multi_extract. No guidance on when not to use it or which alternative is better for other purposes is provided.

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