extract_markdown

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

No annotations are supplied, so the description carries the full behavioral burden. It discloses nothing about authentication, redirect handling, JavaScript rendering, paywalls or bot blocking, truncation behavior, or what happens on failure — behaviors that materially affect how an agent calls a scraper. 'Clean, structured' hints at boilerplate removal but is not a concrete behavioral guarantee.

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?

A single front-loaded sentence with the action and the output artifact stated first and no filler. Nothing in it is redundant or misplaced relative to the schema and annotations.

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-style tool with no output schema, the description is minimally adequate: it states the transformation but not the shape of the result (whether front matter, links, or truncation markers appear). Given there are no annotations to cover safety or failure behavior, a sentence on error/truncation handling would close the remaining gap.

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 url and max_bytes fully documented in the schema including the operator cap on byte limits, so the schema already does the heavy lifting. The description adds no additional meaning about URL constraints or how truncation interacts with returned Markdown, leaving it at the baseline.

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 names a specific verb chain (scrape a web page, convert HTML) and a specific output artifact (clean, structured Markdown), and the 'for LLMs' clause signals the intended consumer. It does not explicitly distinguish itself from the sibling fetch_url, so an agent must infer that this variant is the one that performs HTML-to-Markdown conversion.

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?

Usage is only implied: 'for LLMs' suggests picking this when you want readable page content rather than raw HTML. There is no explicit when-to-use rule, no when-not-to-use, and no named alternative such as fetch_url or web_search, so the routing decision is left to inference.

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