extract_markdown

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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds valuable non-obvious behavior: the whole document is read even when a page subset is requested, running heads and page numbers are dropped, and a server page limit exists. Return shape is partly deferred to the output schema.

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?

Purpose is front-loaded in the first sentence, then formatting behavior, then a structured Args block. The markdown-conversion paragraph is slightly long but each clause (headings, lists, tables, page comments, running heads) conveys real behavior.

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?

An output schema exists, so return values needn't be spelled out, yet the description still explains the markdown structure well enough to interpret results. The one gap is guidance on sibling selection (extract_text vs this tool) for a task that overlaps with several siblings.

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, the description must carry all parameter meaning, and it largely does: path is an absolute local path, pages are 0-based with omit-for-all semantics and a server page limit, and quality's two valid values are named with their meaning. It could be clearer on default pagination fallback when pages exceeds the limit, but coverage is strong.

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 verb (extract) and a precise output format (markdown, reading order) with a clear resource (local PDF). It implicitly differentiates from extract_text/extract_tables by naming its output as reading-order markdown, though it never names those siblings directly.

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 args section says to omit pages for the whole document and explains when quality='balanced' applies (models installed), which implies usage conditions. But there is no explicit guidance on when to choose this tool over extract_text, extract_tables, or extract_blocks, all present as siblings.

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