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

With no annotations, the description carries the full burden and does so unusually well: raw HTML is escaped and never executed, the PDF path loads no network beyond the same public-host guard as html-pdf, and cost is €0.002 per document charged to the API key in the Authorization Bearer header. These are exactly the security, networking and billing facts an agent must know before calling.

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?

Front-loaded with purpose first, then security/cost, then parameters; every clause carries information and nothing is redundant. The trailing semicolon-packed 'Parameters —' run is dense enough to cost some readability, but no sentence is wasted.

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?

Output schema exists, so return values need not be described; the description instead covers cost, auth, sandboxing and every parameter with defaults. Minor gaps remain around source-count rules (markdown vs url exclusivity), input size limits and failure behavior, which an agent might want before a paid 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?

Schema coverage is 0%, so the description must compensate for all five params, and it does: markdown (source text), url (alternative source, .md/.txt), to (html default | pdf | docx), format (A4 default | A3 | A5 | Letter | Legal, gated on to=pdf), margin (example 15mm, gated on to=pdf). Defaults and conditional applicability are supplied where the bare schema has only null-typed strings.

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+resource with scope: GFM Markdown (tables, strikethrough, autolinks) converted to HTML, PDF or DOCX. The output-format list and the markdown-vs-url source model distinguish it clearly from siblings like url_to_markdown, doc_convert and html_pdf.

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?

Explicitly frames 'url' as an alternative source to 'markdown' and gives defaults per target (to=html default; format/margin only apply when to=pdf). It stops short of naming when to prefer doc_convert, html_pdf or url_to_markdown, so routing between similar siblings still needs inference.

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