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

Annotations only declare the generic profile (not read-only, open-world, not idempotent, not destructive); the description adds non-obvious operational constraints — source must be publicly reachable, private-network targets and embedded credentials are rejected, and completion can be awaited or deferred. It still omits cost/quota implications (implied by the get_api_usage sibling) and doesn't warn that repeated calls re-run the conversion since idempotentHint=false.

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 dense sentence with zero filler; the action sequence and the access constraint are front-loaded. It reads as a run-on with three chained clauses, which slightly hurts scannability, but nothing is redundant.

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?

An output schema is present so return values need no explanation, but this is a 9-parameter, open-world network tool with zero schema descriptions, and the description accounts for only 2-3 of those parameters and no failure modes (timeouts, blocked URLs, invalid slug). That is not enough for an agent to invoke it confidently.

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 whole burden and mostly fails: converter 'slug' and the wait/polling switch get light treatment, while width, height, quality, background_color, strip_metadata, and timeout_seconds are never mentioned at all, leaving no hint that the geometry/quality parameters only matter for image-producing converters.

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 concrete pipeline: fetch a public HTML/supported document URL, submit it to HTML.now with a converter slug, optionally wait for the result. This is far more than the name (convert_image_url) or title (HTML document conversion) convey on their own, and the two structured labels conflict, so the description does real disambiguating work — but it never says what the output artifact actually is (rendered image? PDF?) beyond the vague 'convert'.

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 context is only implied: 'optionally wait for the result' hints that wait_for_completion=false hands off to the sibling get_conversion_status, but that tool is never named. No guidance on when to pick this over a different converter, nor when to call list_converters first to obtain a slug, and no exclusion beyond the private-network/credential rejection.

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