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

Beyond the annotations, the description discloses the asynchronous lifecycle, the opaque nature of the returned jobId, the need to poll get_conversion_status, and the user-facing rule not to show the jobId. It also notes the document need not exist in mdedit. This does not contradict the readOnlyHint annotation.

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 with every sentence earning its place: what it converts, the asynchronous workflow, and which sibling to use instead. Purpose is front-loaded and there is no redundant prose.

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 an async conversion tool with fully documented parameters and an output schema, the description supplies the complete invocation pattern: pass content directly, choose a target format, poll with the returned jobId, and use start_article_export for stored documents. Nothing essential for invoking it correctly is missing.

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 description coverage is 100%, so the schema already documents content, to, from, and fileName. The description adds only high-level confirmation (pass content directly) and format examples already present in the schema, so the baseline 3 is appropriate.

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?

The description names a specific verb (Convert), the input resource (Markdown or HTML the caller already has), and concrete output formats (Word, PDF, HTML, LaTeX, EPUB). It also distinguishes itself from start_article_export by clarifying this is for content passed directly, not documents stored in mdedit.

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?

It explicitly states when to use the tool: when content already exists and is passed directly. It also gives the exclusion and alternative: 'To export a document already stored in mdedit, use start_article_export instead,' and routes the caller to get_conversion_status for the asynchronous result.

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