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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false), the description discloses the real operational constraints: the URL must be publicly accessible, private-network targets are rejected (SSRF guard), and embedded credentials are rejected — inputs an agent would otherwise only discover by failing. It stops short of noting that each call creates a new job (relevant given idempotentHint=false) or what happens on converter failure.

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?

A single tight sentence with the action front-loaded and the restrictive constraint (public URL) placed before the rejection rule it explains. No filler. It is arguably too terse for nine parameters, but nothing present is wasted.

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 nine-parameter, open-world, non-idempotent conversion tool with 0% schema descriptions, the description covers only the two required inputs. An output schema exists so return values need no explanation, but an agent still cannot judge what quality, dimensions, strip_metadata, or timeout_seconds do, nor what the non-waiting path yields.

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 0% across 9 parameters, so the description carries the full burden. It explains source_url (publicly accessible, no private ranges, no credentials) and converter (a slug), and alludes to wait_for_completion, but says nothing about width, height, quality, background_color, strip_metadata, or timeout_seconds — six undocumented knobs, several of which materially change output.

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 gives a specific verb chain (download URL -> submit to DOCX.now -> optionally wait) and names the required converter slug, which is far more than a restatement of the name. It does not reconcile the mismatch between the name 'convert_image_url' and the DOCX-document framing, nor does it name the sibling tools it complements (list_converters, get_conversion_status). An agent knows the operation but not precisely which file/media types are in scope.

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?

'optionally wait for the result' hints that wait_for_completion=false is the path to poll via get_conversion_status, but the alternative is never named and no condition is stated for choosing it. There is also no guidance on when a caller should call list_converters first to obtain a valid slug, or when to prefer get_conversion_status over waiting. Usage is implied rather than specified.

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