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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real context beyond that: the return value is an HTML string, and there is a size constraint with a documented out-of-band upload workaround, which an agent would not otherwise know.

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 sentences, front-loaded with what the tool does and what it returns, then the exception for large files. No filler and nothing repeated from structured fields.

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 correctly states the return type, and it handles the main operational wrinkle (large inputs via upload id). The remaining gap is sibling differentiation: an agent cannot tell from this text why preview_markdown exists alongside convert_to_html.

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%, so both parameters (markdown and markdown_upload_id, including the either/or rule and the single-use 10-minute expiry) are already fully documented in the schema. The description reinforces the upload id path but adds no semantics the schema lacks, so the baseline of 3 applies.

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 ('Converts markdown to HTML') plus the framing that the output shows how it will look as a Word document, so the agent knows what it gets back. However, it never distinguishes itself from the sibling convert_to_html, which on its face sounds like the same operation, leaving the agent to guess which one to pick.

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 by the word 'preview' and the Word-document framing; there is no explicit statement of when to use this over convert_to_docx or convert_to_html. The one concrete usage rule given is the large-file path (POST to /mcp/upload, then pass the id), which is genuinely helpful workflow guidance but covers only an edge case.

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