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

Annotations already declare readOnlyHint and openWorldHint, so the bar is lower, and the description adds real behavioral context the annotations cannot: per-call pricing ('$0.006 USDC per call (x402)') and the return-mode distinction that text formats come back inline. It still doesn't say how binary/non-text results are delivered, which is the main gap.

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?

Three tight sentences, front-loaded with capability, then invocation, then cost. Dense and every sentence carries information, though the format enumeration is long enough to bloat the opening slightly.

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 9-parameter paid tool with no output schema, the definition covers purpose, price, and text-return behavior but omits how binary/file outputs are returned (base64 vs stored links) and gives no guidance on the four undocumented parameters. Adequate but with visible holes.

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 only 44% (to, toc, title, from are bare), so the description ought to compensate more. It adds some value by distinguishing text input from file input and by implying format-directed conversion, but adds nothing about toc, title, or the 'to'/'from' format vocabulary.

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 and resource ('Universal document converter (Pandoc)') and enumerates the supported formats ('Markdown, HTML, Word, OpenDocument, EPUB, LaTeX...'), making the scope unmistakable. The breadth claim ('any direction') clearly separates it from narrower siblings like office_convert.

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 usage ('Send text or a file; text formats come back inline') but never states when to choose this tool over the close siblings office_convert, convert, or media_convert. No exclusion conditions or explicit alternative routing are given, leaving selection to inference.

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