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

Goes well beyond the annotations (which only cover readOnly/openWorld/idempotent/destructive) by disclosing the async job model, that it returns a job_id immediately, the 5s polling cadence, the next tools to call, the flat $0.05 fee, and sandbox-safety in claude.ai/Desktop/Cursor. This is exactly the mutation-lifecycle context annotations cannot express.

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?

Long but front-loaded: purpose first, then routing guidance, then the async workflow and pricing. Nearly every sentence carries actionable information, though 'Runs entirely server-side' is stated twice and the density is slightly high for a two-parameter tool.

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?

Despite an output schema existing, the description supplies the missing operational context an agent needs: the async polling loop, the two terminal retrieval tools, format support, and cost. Nothing needed to invoke or follow up on this tool is absent.

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 already 100%, so baseline is 3, but the description adds real meaning: it enumerates supported input formats (md, html, rst, txt, docx) and output formats (docx, pdf, html, txt, md, rst, xlsx) and explains that share links auto-resolve to a file, which clarifies source_url semantics beyond 'Public HTTPS URL'.

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 (document conversion from a public URL) and distinguishes itself from siblings by naming convert_content and by scope of input source. An agent can tell it apart from convert_file, convert_content, and the transcode/conform/transcribe families without opening any schema.

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 says when to use it (source document is at a public URL; Dropbox/Drive/OneDrive/SharePoint/Box share links auto-resolve) and when not to (if content is already a string, use convert_content; for files too large for convert_content's 4 MB inline limit). Names the alternative and the selecting condition.

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