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

Goes well beyond the annotations by disclosing the paid nature ('500 micro-dollar service credits per successful call'), the dependency on credits and auth header, and the billing behavior around requestId. This is valuable operational context not present in structured fields.

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?

Every sentence earns its place: purpose, cost, prerequisite, auth, and recovery are all front-loaded and stated with minimal words. No filler or repetition.

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 requiring preparation, the description covers the full lifecycle: what it does, how to set it up, what to expect in terms of billing, and how to recover without extra charges. The presence of an output schema also handles return-value expectations.

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 covers requestId and maxPriceMicroUsd with descriptions, but the tool description adds meaning to requestId ('Reuse prepared arguments for recovery; a new requestId is a new billable operation') and maps 'input' to the HTML being extracted. It does not explain maxPriceMicroUsd in the description, but schema coverage is already strong.

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 the action ('Extract article text') and resource ('supplied HTML'), which differentiates it from sibling tools like html_links, html_tables, or html_metadata. No ambiguity about what this tool does.

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?

Provides explicit prerequisites: 'First use agent_utilities_prepare', requires credits and a private Authorization header. It gives recovery guidance but does not explicitly contrast this tool against siblings or state when not to use it.

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