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

Discloses two traits invisible in annotations: raw HTML in the input is escaped so output is safe to embed (a security-relevant behavior), and each successful call costs $0.001 USDC on Base via x402. The payment note also explains why annotations mark the call non-read-only despite being a pure conversion.

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: capability first, safety second, usage-and-cost last. No filler, and the most decision-relevant information is front-loaded.

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?

With no output schema, the description implies the return is embeddable HTML but never states the response shape or field name. Everything else an agent needs to call it correctly (input format, safety, cost) is present.

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% but the parameter description is only 'The Markdown', so the description carries the real semantic load by specifying which Markdown features are understood. It does not discuss size limits or how unsupported syntax is handled.

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 ('Convert Markdown ... to HTML') and enumerates the supported constructs (headings, code, lists, tables-adjacent features), so the agent knows exactly what transformation is performed. It is clearly distinguishable from siblings like html_to_text, which does the inverse.

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?

Gives a concrete usage context: 'Use to publish agent-written Markdown on a web page.' It does not name alternatives (e.g., html_to_text for the opposite direction) or state when-not to use it, but the intended scenario is unambiguous.

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