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

Annotations already mark idempotentHint=true and readOnlyHint=false, but the description adds significant behavioral context beyond them: the 300 micro-dollar cost, the required prepare step, the private Authorization header, and the billing distinction between reused and new requestIds. No contradiction with 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 with the core purpose, followed by essential usage and cost details. Each sentence earns its place, and the structure allows quick scanning by an agent.

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 paid tool with required preparation, the description covers prerequisites, billing, authorization, recovery, and output limits. Since an output schema exists, return-value details are not needed. The description plus schema provides what an agent needs to call this tool correctly.

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 descriptions already cover requestId and maxPriceMicroUsd, and the description reinforces their recovery and billing semantics. However, the input.html and baseUrl fields are not explicitly explained; the description only implies HTML input through the extraction behavior and does not clarify baseUrl's role.

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 opens with a specific verb and resource: 'Extract up to 200 image URLs, alt text and source attributes'. It clearly states what the tool does and what it does not do ('does not fetch images'), which distinguishes it from sibling tools like html_links or web_readable_fetch.

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?

The description gives solid when-to-use context: prerequisites (agent_utilities_prepare), credits, authorization, and recovery behavior. It does not explicitly name alternatives or state when not to use this tool, but the negative clause 'does not fetch images' partly serves that role.

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