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

Annotations already provide idempotent and non-destructive hints. The description goes further by disclosing that JavaScript is not executed, that external fonts/images are allowed, the 1-credit cost, and the 15-minute link expiry. These are valuable behavioral constraints not captured in annotations.

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?

The description is compact and front-loaded: it opens with the exact output format, then efficiency notes, use cases, and mode selection. Every sentence adds value—including the credit cost and link instruction—with no redundancy or fluff.

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 tool with 10 parameters and no output schema, the description adequately covers core workflow (html vs template+data), returns a temporary link, and instructs the agent to include it in replies. The schema fills parameter details; the description adds the credit cost and link behavior. Minor missing info on error handling but not essential for successful invocation.

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% with detailed parameter descriptions. The tool description adds context beyond the schema: it clarifies that CSS must be inline or in a style tag, that JavaScript won't run, and explains the html-vs-template+data relationship. This enriches the agent's understanding without repeating schema text.

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 clearly states it renders HTML into an image (PNG, JPEG, WebP) and lists concrete use cases (social cards, certificates, tickets, OG images). It distinguishes from siblings like html_to_pdf (PDF) and screenshot_url (URL) by specifying input is raw HTML.

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 explains when to use it ('Ideal for social cards, certificates, tickets...') and describes the two modes of use (html vs template+data). However, it doesn't explicitly contrast with sibling tools or state when not to use it, leaving some inference to the agent.

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